Upload 19 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "abacusai/Smaug-34B-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 200000,
+  "model_type": "mixtral",
+  "num_attention_heads": 56,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

mergekit_moe_config.yml

@@ -0,0 +1,63 @@
+base_model: abacusai/Smaug-34B-v0.1
+gate_mode: hidden
+dtype: bfloat16
+experts:
+  - source_model: cognitivecomputations/dolphin-2.2-yi-34b-200k
+    positive_prompts:
+      - "Help me debug this Python script."
+      - "Rewrite this JavaScript function to use arrow functions."
+      - "Optimize this C# script for better performance."
+      - "Implement a REST API using Node.js."
+      - "Convert this procedural PHP code into object-oriented PHP."
+      - "Assist me with writing a Python program that solves linear equations."
+      - "Explain the concept of recursion in programming."
+      - "Give an overview of the Model-View-Controller (MVC) architecture."
+      - "Compare and contrast between functional and object-oriented programming."
+      - "Provide information about state management in React."
+      - "Help me understand asynchronous programming in JavaScript."
+      - "Summarize the differences between SQL and NoSQL databases."
+      - "Make a recommendation on the best algorithm for sorting large datasets."
+      - "Answer this question about Python's memory management."
+    negative_prompts:
+      - "Write an essay on"
+      - "Explain the historical significance of"
+      - "Summarize the plot of"
+      - "Provide a detailed analysis on"
+      - "Discuss the philosophical implications of"
+      - "Review this book/movie"
+      - "Explain the theory behind"
+      - "Describe the cultural impact of"
+      - "Give your opinion on"
+      - "Narrate a story about"
+      - "Critique this artwork"
+      - "Analyze this poem"
+      - "Compare and contrast the political systems of"
+      - "Discuss the social dynamics of"
+
+  - source_model: abacusai/Smaug-34B-v0.1 
+    positive_prompts:
+      - "Discuss the impact of renewable energy sources on global economies."
+      - "Analyze the role of technology in enhancing modern education systems."
+      - "Evaluate the effects of social media on adolescent mental health."
+      - "Explain the principles of sustainable urban planning."
+      - "Critique the ethical implications of artificial intelligence in healthcare."
+      - "Compare and contrast classical and modern theories of economics."
+      - "Outline the challenges and solutions in achieving universal healthcare."
+      - "Assess the influence of globalization on cultural identity."
+      - "Review the development and impact of blockchain technology."
+      - "Explore the relationship between climate change and biodiversity loss."
+      - "Summarize the key arguments in the debate on net neutrality."
+      - "Examine the history and evolution of computational linguistics."
+      - "Investigate the potential of gene editing technologies for disease prevention."
+      - "Discuss the significance of quantum computing in solving complex problems."
+      - "Analyze the social and political factors affecting immigration policies."
+      - "Evaluate the role of leadership in organizational success."
+      - "Explain the concept of circular economy and its benefits."
+      - "Critique the methods and outcomes of contemporary educational reforms."
+      - "Compare the efficacy of different psychological approaches to treating anxiety."
+      - "Outline the advancements and challenges in renewable energy storage technologies."
+    negative_prompts:
+      - "help with debugging or coding in Python, JavaScript, C#, PHP, or Node.js"
+      - "optimizing algorithms or writing code snippets"
+      - "advice on implementing software features or choosing programming languages"
+      - "converting code between languages or understanding programming paradigms"

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d8c8e2d178bda95a35adb5699df87ac311e967998c47eaec3a631a4ed996ea
+size 9953233480

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07de936f592d554045669cb01e39ce0dc88b35a4b4964b0af7a71cde433b8ea
+size 9982594336

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d573a6826a41e6b0571de8dc730293d275c44b43f8348db3e54cd1bc84d084a5
+size 9982594384

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89a7e520f84a2b5ee07b76a2c65463855a0bc9848cd29dbe469955b3de3d3df
+size 9982594392

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36112a492c340aca31b2b2e8832543f5d2ec6ca829c9f1708a246d842be90a08
+size 9982594392

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a4422fe0419c6e06221736fa9f1a8b0dd0791e29242df35aeb31c278cc24a0
+size 9982594392

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e802665111d7113e0228039c629893e3e6b52ded6875727020abef361ba79de4
+size 9982594392

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa19cb31f36e9f684c339e8784703a5820b92b1bc777a494aaf218ac9803fa2
+size 9982594392

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455a19f83e89e768f821e4b3d81b83232ca14f4f1eadd33ed3923f768a17a619
+size 9982594392

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5f8ca77bdec573f8f4848bcb1908de17f281f08e740baa2a6bcaafd7615a440
+size 9982594392

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d4610b7aaeaff329a12c3b88cea11766bb1a2c073f32361c869d1dd78b3566
+size 9982594392

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f17e91feb58b0ff27f2fc7da11f4724c404a3281802762f7b826887965f72b2
+size 9982594392

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056932984cc8788977d828c04a340ee6f226e5e9d511ce8af9150060290f5c3
+size 1866110632

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00013.safetensors", "model.norm.weight": "model-00001-of-00013.safetensors", "lm_head.weight": "model-00001-of-00013.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00013.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00013.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00013.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00013.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00013.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00013.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00013.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00013.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00013.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00013.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00013.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00013.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00013.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00013.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00013.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00013.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00013.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00013.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00013.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00013.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00013.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00013.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00013.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00013.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00013.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00013.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00013.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00013.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00013.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00013.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00013.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00013.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00013.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00013.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00013.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00013.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00013.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00013.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00013.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00013.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00013.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00013.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00013.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00013.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00013.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00013.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00013.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00013.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00013.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00013.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00013.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00013.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00013.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00013.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00013.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00013.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00013.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00013.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00013.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00013.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00013.safetensors", "model.layers.48.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00013.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00013.safetensors", "model.layers.49.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00013.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00013.safetensors", "model.layers.50.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00013.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00013.safetensors", "model.layers.51.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00013.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00013.safetensors", "model.layers.52.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00013.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00013.safetensors", "model.layers.53.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00013.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00013.safetensors", "model.layers.54.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00013.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00013.safetensors", "model.layers.55.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00013.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00013.safetensors", "model.layers.56.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00013.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00013.safetensors", "model.layers.57.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00013.safetensors", "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00013.safetensors", "model.layers.58.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00013.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00013.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.48.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.49.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.50.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.51.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.52.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.53.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.54.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.55.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.56.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.57.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.58.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors", "model.layers.59.block_sparse_moe.gate.weight": "model-00013-of-00013.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}