Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

mergekit_moe_config.yml

@@ -0,0 +1,68 @@
+base_model: google/gemma-7b
+gate_mode: random
+dtype: bfloat16
+experts_per_token: 2
+experts:
+  - source_model: Crystalcareai/gemma-mod
+    positive_prompts:
+      - "What are some fun activities to do this weekend in Seattle?"
+      - "Can you recommend a good Italian restaurant in New York City?"
+    negative_prompts:
+      - "Write a Python script to scrape data from a website."
+      - "Explain the key differences between Bayesian and frequentist statistics."
+      
+  - source_model: Crystalcareai/gemma-orca
+    positive_prompts:
+      - "What are the potential long-term economic impacts of raising the minimum wage?"
+      - "Analyze the logical fallacies in the following argument: [example argument]"  
+    negative_prompts:
+      - "Write a heartfelt poem about the beauty of nature."
+      - "What year did World War II end?"
+      
+  - source_model: Crystalcareai/gemma-codefeedback
+    positive_prompts:
+      - "Can you review my JavaScript code and suggest ways to optimize it for better performance?"
+      - "I'm getting an 'undefined variable' error in my Python script. Here's the code: [code snippet]"
+    negative_prompts:
+      - "What are some effective strategies for managing stress and anxiety?"
+      - "Compare and contrast the themes in 'The Great Gatsby' and 'The Catcher in the Rye'."
+      
+  - source_model: Crystalcareai/gemma-coder
+    positive_prompts:
+      - "How do I implement a binary search tree in C++?"  
+      - "What's the best way to connect to a PostgreSQL database using Java?"
+    negative_prompts:
+      - "What were the main causes of the French Revolution?"
+      - "Suggest some healthy meal ideas for someone on a vegan diet."
+      
+  - source_model: Crystalcareai/gemma-roleplay
+    positive_prompts:  
+      - "Let's roleplay a scene where I'm a knight and you're a dragon. I'll start: 'Foul beast! I have come to vanquish you!'"
+      - "Pretend you're a wise old tree and I'm a curious child. I'll ask: 'Tell me, ancient one, what secrets do you keep?'"
+    negative_prompts:
+      - "What is the capital of Bulgaria?"
+      - "Explain how a combustion engine works."
+      
+  - source_model: Crystalcareai/Gemma-Generic  
+    positive_prompts:
+      - "What are the key differences between Buddhism and Hinduism?"
+      - "How does photosynthesis work in plants?"
+    negative_prompts:
+      - "Debug the following block of Rust code: [code]"
+      - "I need help figuring out how much I should save each month for retirement."
+      
+  - source_model: Crystalcareai/gemma-Selfdiscover
+    positive_prompts:
+      - "Please make a reservation for 2 at Che Fico at 7pm this Friday night."
+      - "Set a daily reminder for me to take my vitamins at 9am starting tomorrow."
+    negative_prompts:
+      - "What do you think about the current state of politics in America?"
+      - "I'm feeling really down lately. Do you have any advice to cheer me up?"
+      
+  - source_model: Crystalcareai/Gemma-COT 
+    positive_prompts:
+      - "What is 27 * 49? Show your step-by-step work."
+      - "Describe the process for changing a flat tire, with detailed steps in order."
+    negative_prompts:
+      - "Write a short science fiction story about space travel."
+      - "Who painted the Mona Lisa?"

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79523bf909590539f3c8ee6dec6c04118ebb189ef4c61e7942bee99be908090f
+size 9877638200

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f520ea6ae4538ae03f30cc54d872789bfb2b54b401c194b213a65d4afc93769
+size 9865037392

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36112d4e63f7f9fe66927bc2494a5f81b1e97ce58ec9f9ce47bd41cded46551
+size 9965713672

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2acd426dff4682c8919679cc8228a9bb15a0618c74a0e26e5cbcc51c83e3992
+size 9965713672

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c7362d75bf79502eb4125c32ea95180bc47247679e7da923bc852685d78e6c
+size 9865037464

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9856bb6c5b52c1f925d4db640a5359aebac381c6e9b8cbe928f6d3380beae24
+size 9965713752

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30edfe693396eca8cfbacc7487fa3fbd4c4cb6e6b16291cd401fc0e4d9c88a61
+size 9965713752

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e303ded5a1e2e845c04b4fd637304a6c59b1d4cba51cfc9638a6d753f7025231
+size 9865037464

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9166009dcb520305020c52d8431bcc9bf8a9ad2b1d55bbb60f061080d9c7b8df
+size 9965713752

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b5bbdda3768c0800e5b292085c30fd35885e348f5ba64349a28708c750cb24
+size 9965713752

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0564030c53d931abe736aa52ae942ccb679e5efe797f46f5355256d85e5b3271
+size 6594844032

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.norm.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00011.safetensors", "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00011.safetensors", "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00011.safetensors", "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00011.safetensors", "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00011.safetensors", "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00011.safetensors", "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00011.safetensors", "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00011.safetensors", "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00011.safetensors", "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00011.safetensors", "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00011.safetensors", "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00011.safetensors", "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00011.safetensors", "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00011.safetensors", "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00011.safetensors", "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00011.safetensors", "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00011.safetensors", "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00011.safetensors", "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00011.safetensors", "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00011.safetensors", "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00011.safetensors", "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00011.safetensors", "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00011.safetensors", "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00011.safetensors", "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00011.safetensors", "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00011.safetensors", "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00011.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<bos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}