Text Generation
Transformers
Safetensors
English
smallthinker
feature-extraction
conversational
custom_code
Instructions to use Tiiny/SmallThinker-4BA0.6B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tiiny/SmallThinker-4BA0.6B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Tiiny/SmallThinker-4BA0.6B-Instruct", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Tiiny/SmallThinker-4BA0.6B-Instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Tiiny/SmallThinker-4BA0.6B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tiiny/SmallThinker-4BA0.6B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tiiny/SmallThinker-4BA0.6B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Tiiny/SmallThinker-4BA0.6B-Instruct
- SGLang
How to use Tiiny/SmallThinker-4BA0.6B-Instruct with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Tiiny/SmallThinker-4BA0.6B-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tiiny/SmallThinker-4BA0.6B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Tiiny/SmallThinker-4BA0.6B-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tiiny/SmallThinker-4BA0.6B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Tiiny/SmallThinker-4BA0.6B-Instruct with Docker Model Runner:
docker model run hf.co/Tiiny/SmallThinker-4BA0.6B-Instruct
| { | |
| "metadata": { | |
| "total_size": 8536919040 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00002-of-00002.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.0.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.0.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.0.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.1.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.1.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.1.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.10.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.10.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.10.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.11.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.11.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.11.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.12.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.12.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.12.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.13.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.13.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.13.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.14.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.14.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.14.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.15.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.15.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.15.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.16.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.16.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.16.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.17.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.17.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.17.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.18.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.18.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.18.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.19.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.19.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.19.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.2.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.2.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.2.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.20.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.20.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.20.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.21.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.21.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.21.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.22.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.22.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.22.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.23.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.23.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.23.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.24.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.24.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.24.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.25.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.25.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.25.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.26.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.26.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.26.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.27.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.27.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.27.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.28.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.28.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.28.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.29.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.29.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.29.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.3.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.3.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.3.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.30.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.30.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.30.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.31.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.31.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.31.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.4.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.4.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.4.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.5.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.5.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.5.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.6.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.6.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.6.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.7.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.7.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.7.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.8.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.8.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.8.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.9.down.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.9.gate.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.experts.9.up.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.block_sparse_moe.primary_router.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.down.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.up.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.primary_router.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.norm.weight": "model-00002-of-00002.safetensors" | |
| } | |
| } | |