Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "patched-codes/patched-coder-7b-8k-context",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100018
+}

.ipynb_checkpoints/mergekit_moe_config-checkpoint.yml

@@ -0,0 +1,22 @@
+base_model: patched-codes/patched-coder-7b-8k-context
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+experts_per_token: 1
+experts:
+  - source_model: patched-codes/patched-fixer-7b-8k-context
+    positive_prompts:
+      - 'You are a senior software engineer who is best in the world at fixing vulnerabilities.\nUsers will give you vulnerable code and you will generate a fix based on the provided INSTRUCTION.\nINSTRUCTION:'
+    ## (optional)
+    # negative_prompts:
+    #   - "This is a prompt expert_model_1 should not be used for"
+  - source_model: patched-codes/patched-analyzer-7b-8k-context
+    positive_prompts:
+      - 'You are a senior security researcher who is best in the world at detecting vulnerabilities.\nCarefully analyze the given code snippet and track the data flows from various sources to sinks.\nAssume that any call to an unknown external API is not sanitized.\nRespond only with either "YES" or "NO".'
+  # ... and so on
+  - source_model: patched-codes/patched-committer-7b-8k-context
+    positive_prompts:
+      - 'You are a software engineer who is best in the world at summarizing code changes.\nCarefullly analyze the given old code and new code and generate a summary of the changes.'
+  - source_model: patched-codes/patched-coder-7b-8k-context
+    positive_prompts:
+      - 'You are a coding assitant, who is best in the world at debugging.'

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "patched-codes/patched-coder-7b-8k-context",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 100018
+}

mergekit_moe_config.yml

@@ -0,0 +1,22 @@
+base_model: patched-codes/patched-coder-7b-8k-context
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+## (optional)
+experts_per_token: 1
+experts:
+  - source_model: patched-codes/patched-fixer-7b-8k-context
+    positive_prompts:
+      - 'You are a senior software engineer who is best in the world at fixing vulnerabilities.\nUsers will give you vulnerable code and you will generate a fix based on the provided INSTRUCTION.\nINSTRUCTION:'
+    ## (optional)
+    # negative_prompts:
+    #   - "This is a prompt expert_model_1 should not be used for"
+  - source_model: patched-codes/patched-analyzer-7b-8k-context
+    positive_prompts:
+      - 'You are a senior security researcher who is best in the world at detecting vulnerabilities.\nCarefully analyze the given code snippet and track the data flows from various sources to sinks.\nAssume that any call to an unknown external API is not sanitized.\nRespond only with either "YES" or "NO".'
+  # ... and so on
+  - source_model: patched-codes/patched-committer-7b-8k-context
+    positive_prompts:
+      - 'You are a software engineer who is best in the world at summarizing code changes.\nCarefullly analyze the given old code and new code and generate a summary of the changes.'
+  - source_model: patched-codes/patched-coder-7b-8k-context
+    positive_prompts:
+      - 'You are a coding assitant, who is best in the world at debugging.'

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dc8795b6bc338e65e600266a708f7ce5ff5e8df3179bff485221b48267c158
+size 9972915800

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb4dab51b282b653011d669067617a3c018141ab628ce7e4a0d86e909ce17fb
+size 9978407360

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c4643fe4350663ecb9da1b591649bb0fc564d5204a75c3f8845e06c35f86c6
+size 9978407424

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38361d811dc661d04dbf9255b4e14d84aca76d980296829d7ad87c0aacb2fa18
+size 8200964184

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 38130622464}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_start|>"
+}

tokenizer_config.json

@@ -0,0 +1,165 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100015": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100016": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100017": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|im_start|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}