Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "Qwen/Qwen2-1.5B",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 8960,
+  "norm_topk_prob": true,
+  "num_attention_heads": 12,
+  "num_experts": 2,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 8960,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_moe_config.yml

@@ -0,0 +1,25 @@
+
+base_model: Qwen/Qwen2-1.5B
+architecture: qwen
+experts:
+  - source_model: Qwen/Qwen2-1.5B
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "I want"
+  - source_model: Replete-AI/Replete-Coder-Qwen2-1.5b
+    positive_prompts:
+    - "code"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+shared_experts:
+  - source_model: Qwen/Qwen2-1.5B
+    positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed
+      - "chat"
+    # (optional, but recommended:)
+    residual_scale: 0.1 # downweight output from shared expert to prevent overcooking the model
+

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204f040004e1be74b8e3c0a2f3d0c7400e8b1e95596a4a0ece58e87fea4ef0a0
+size 4975576504

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f823da54d97dd704badb5db0eeeeb9db039936eec8f4fb9556802432913892d5
+size 3203144672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 8178654208}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.shared_expert.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.shared_expert.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.0.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.1.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.shared_expert.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.0.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.experts.1.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.shared_expert.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors", "model.layers.0.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.0.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.1.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.2.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.2.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.10.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.10.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.11.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.11.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.12.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.12.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.13.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.13.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.14.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.14.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.15.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.15.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.16.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.16.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.17.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.18.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.25.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.26.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.gate.weight": "model-00002-of-00002.safetensors", "model.layers.27.mlp.shared_expert_gate.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}