Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+base_model:
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+- NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+---
+
+# moe-minicpm-x4-base
+
+moe-minicpm-x4-base is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [NurtureAI/minicpm-2b-sft-bf16-llamafied-16k](https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k)
+* [NurtureAI/minicpm-2b-sft-bf16-llamafied-16k](https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k)
+* [NurtureAI/minicpm-2b-sft-bf16-llamafied-16k](https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k)
+* [NurtureAI/minicpm-2b-sft-bf16-llamafied-16k](https://huggingface.co/NurtureAI/minicpm-2b-sft-bf16-llamafied-16k)
+
+## 🧩 Configuration
+
+```yaml
+base_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+gate_mode: random
+experts_per_token: 2
+experts:
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "babybirdprd/moe-minicpm-x4-base"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "NurtureAI/minicpm-2b-sft-bf16-llamafied-16k",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dim_model_base": 256,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2304,
+  "initializer_range": 0.1,
+  "intermediate_size": 5760,
+  "max_position_embeddings": 16384,
+  "model_type": "mixtral",
+  "num_attention_heads": 36,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 36,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 122753
+}

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+
+base_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+gate_mode: random
+experts_per_token: 2
+experts:
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]
+  - source_model: NurtureAI/minicpm-2b-sft-bf16-llamafied-16k
+    positive_prompts: [""]

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8afb4023f14958f36836c726f2b8702ca82172f04a9372882e8857d7d5c7fc7
+size 1975367976

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd708206c0476a9b4e049e224d1082a3d3e6477655757cbca423b9b9eb623db
+size 1990714224

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7df0a3e4bc982a304a472253fcc60fd06508aaa31068db5f1a1ddfce728a804
+size 1980107104

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe495b8c783528f5cbcb26fe30d902c560e9ee63c10f9918c49d3636b22d3da
+size 1990714320

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05eef36be9d95eff29e4af1e151300c06e71a2a29768b38237bee2fe3d490332
+size 1980107144

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:956ef109cd9ff63ff0cb37c9f11fd879d85eab858b9087f06d9de7abfe4a157a
+size 1990714320

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96755a3af3cabf9213bb4dd34a81d9d83062e30e6ba9e015bb36f7a16762085
+size 1980107144

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:799a304070fc5e9b30fb71df911384fec0f0d877678f577763d83cb4d3687e01
+size 1683556784

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.norm.weight": "model-00001-of-00008.safetensors", "lm_head.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aafcd7da1f5611dab6be545db74d5552a2ccc9c2a12c72ea7be63aac4a25d7
+size 1994871

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}