Upload folder using huggingface_hub

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- epfl-llm/meditron-7b
+- medalpaca/medalpaca-7b
+- chaoyi-wu/PMC_LLAMA_7B_10_epoch
+- allenai/tulu-2-dpo-7b
+---
+
+# Mediquad-tulu-20B
+
+Mediquad-tulu-20B is a Mixure of Experts (MoE) made with the following models:
+* [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b)
+* [medalpaca/medalpaca-7b](https://huggingface.co/medalpaca/medalpaca-7b)
+* [chaoyi-wu/PMC_LLAMA_7B_10_epoch](https://huggingface.co/chaoyi-wu/PMC_LLAMA_7B_10_epoch)
+* [allenai/tulu-2-dpo-7b](https://huggingface.co/allenai/tulu-2-dpo-7b)
+
+## 🧩 Configuration
+
+```yamlbase_model: allenai/tulu-2-dpo-7b
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: epfl-llm/meditron-7b
+    positive_prompts:
+      - "What are the latest guidelines for managing type 2 diabetes?"
+      - "Best practices for post-operative care in cardiac surgery are"
+    negative_prompts:
+      - "What are the environmental impacts of deforestation?"
+      - "The recent advancements in artificial intelligence have led to developments in"
+  - source_model: medalpaca/medalpaca-7b
+    positive_prompts:
+      - "When discussing diabetes management, the key factors to consider are"
+      - "The differential diagnosis for a headache with visual aura could include"
+    negative_prompts:
+      - "Recommend a good recipe for a vegetarian lasagna."
+      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
+  - source_model: chaoyi-wu/PMC_LLAMA_7B_10_epoch
+    positive_prompts:
+      - "How would you explain the importance of hypertension management to a patient?"
+      - "Describe the recovery process after knee replacement surgery in layman's terms."
+    negative_prompts:
+      - "Recommend a good recipe for a vegetarian lasagna."
+      - "The recent advancements in artificial intelligence have led to developments in"
+      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
+  - source_model: allenai/tulu-2-dpo-7b
+    positive_prompts:
+      - "Here is a funny joke for you -"
+      - "When considering the ethical implications of artificial intelligence, one must take into account"
+      - "In strategic planning, a company must analyze its strengths and weaknesses, which involves"
+      - "Understanding consumer behavior in marketing requires considering factors like"
+      - "The debate on climate change solutions hinges on arguments that"
+    negative_prompts:
+      - "In discussing dietary adjustments for managing hypertension, it's crucial to emphasize"
+      - "For early detection of melanoma, dermatologists recommend that patients regularly check their skin for"
+      - "Explaining the importance of vaccination, a healthcare professional should highlight"
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Technoculture/Mediquad-tulu-20B"
+
+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"])
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|im_end|>": 32002,
+  "<|im_start|>": 32001,
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "allenai/tulu-2-dpo-7b",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,38 @@
+base_model: allenai/tulu-2-dpo-7b
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: epfl-llm/meditron-7b
+    positive_prompts:
+      - "What are the latest guidelines for managing type 2 diabetes?"
+      - "Best practices for post-operative care in cardiac surgery are"
+    negative_prompts:
+      - "What are the environmental impacts of deforestation?"
+      - "The recent advancements in artificial intelligence have led to developments in"
+  - source_model: medalpaca/medalpaca-7b
+    positive_prompts:
+      - "When discussing diabetes management, the key factors to consider are"
+      - "The differential diagnosis for a headache with visual aura could include"
+    negative_prompts:
+      - "Recommend a good recipe for a vegetarian lasagna."
+      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
+  - source_model: chaoyi-wu/PMC_LLAMA_7B_10_epoch
+    positive_prompts:
+      - "How would you explain the importance of hypertension management to a patient?"
+      - "Describe the recovery process after knee replacement surgery in layman's terms."
+    negative_prompts:
+      - "Recommend a good recipe for a vegetarian lasagna."
+      - "The recent advancements in artificial intelligence have led to developments in"
+      - "The fundamental concepts in economics include ideas like supply and demand, which explain"
+  - source_model: allenai/tulu-2-dpo-7b
+    positive_prompts:
+      - "Here is a funny joke for you -"
+      - "When considering the ethical implications of artificial intelligence, one must take into account"
+      - "In strategic planning, a company must analyze its strengths and weaknesses, which involves"
+      - "Understanding consumer behavior in marketing requires considering factors like"
+      - "The debate on climate change solutions hinges on arguments that"
+    negative_prompts:
+      - "In discussing dietary adjustments for managing hypertension, it's crucial to emphasize"
+      - "For early detection of melanoma, dermatologists recommend that patients regularly check their skin for"
+      - "Explaining the importance of vaccination, a healthcare professional should highlight"
+

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555cecf7c5e15b26eb58201ab1c5a19199e02d94f76c8f6598579cb8f5ce3a9d
+size 9993217320

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f18d7637c820216fd3de09f8e6d30c37481aa0dbb9c6fdaba8e9475ffce9c12
+size 9919543448

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f897f9f19d11ca52f5e7eca2bae0c3212e4b8a9c309b150bc2f3b0e0ffb84f1
+size 9919543448

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5270860c26b1d7bbb1f7f8b0a449dd68d1e6a7eda355b7855eeed4d6c1fee1
+size 9616783112

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}