Add files using upload-large-folder tool

.gitattributes

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

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1745846118

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,1369 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 140000,
+  "max_window_layers": 94,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 1536,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 94,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "qkv_bias": false,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "modules_to_not_convert": [
+      "lm_head",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.k_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.23.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.28.mlp.shared_expert_gate",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert_gate",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.29.self_attn.v_proj.bias",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.31.mlp.shared_expert_gate",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert_gate",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert_gate",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert_gate",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert_gate",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert_gate",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert_gate",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.k_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert_gate",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert_gate",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert_gate",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert_gate",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert_gate",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.v_proj.bias",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.k_proj.bias",
+      "model.layers.46.self_attn.q_proj.bias",
+      "model.layers.46.self_attn.v_proj.bias",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert_gate",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.k_proj.bias",
+      "model.layers.47.self_attn.q_proj.bias",
+      "model.layers.47.self_attn.v_proj.bias",
+      "model.layers.48.input_layernorm",
+      "model.layers.48.mlp.gate",
+      "model.layers.48.mlp.shared_expert_gate",
+      "model.layers.48.post_attention_layernorm",
+      "model.layers.48.self_attn.k_proj.bias",
+      "model.layers.48.self_attn.q_proj.bias",
+      "model.layers.48.self_attn.v_proj.bias",
+      "model.layers.49.input_layernorm",
+      "model.layers.49.mlp.gate",
+      "model.layers.49.mlp.shared_expert_gate",
+      "model.layers.49.post_attention_layernorm",
+      "model.layers.49.self_attn.k_proj.bias",
+      "model.layers.49.self_attn.q_proj.bias",
+      "model.layers.49.self_attn.v_proj.bias",
+      "model.layers.50.input_layernorm",
+      "model.layers.50.mlp.gate",
+      "model.layers.50.mlp.shared_expert_gate",
+      "model.layers.50.post_attention_layernorm",
+      "model.layers.50.self_attn.k_proj.bias",
+      "model.layers.50.self_attn.q_proj.bias",
+      "model.layers.50.self_attn.v_proj.bias",
+      "model.layers.51.input_layernorm",
+      "model.layers.51.mlp.gate",
+      "model.layers.51.mlp.shared_expert_gate",
+      "model.layers.51.post_attention_layernorm",
+      "model.layers.51.self_attn.k_proj.bias",
+      "model.layers.51.self_attn.q_proj.bias",
+      "model.layers.51.self_attn.v_proj.bias",
+      "model.layers.52.input_layernorm",
+      "model.layers.52.mlp.gate",
+      "model.layers.52.mlp.shared_expert_gate",
+      "model.layers.52.post_attention_layernorm",
+      "model.layers.52.self_attn.k_proj.bias",
+      "model.layers.52.self_attn.q_proj.bias",
+      "model.layers.52.self_attn.v_proj.bias",
+      "model.layers.53.input_layernorm",
+      "model.layers.53.mlp.gate",
+      "model.layers.53.mlp.shared_expert_gate",
+      "model.layers.53.post_attention_layernorm",
+      "model.layers.53.self_attn.k_proj.bias",
+      "model.layers.53.self_attn.q_proj.bias",
+      "model.layers.53.self_attn.v_proj.bias",
+      "model.layers.54.input_layernorm",
+      "model.layers.54.mlp.gate",
+      "model.layers.54.mlp.shared_expert_gate",
+      "model.layers.54.post_attention_layernorm",
+      "model.layers.54.self_attn.k_proj.bias",
+      "model.layers.54.self_attn.q_proj.bias",
+      "model.layers.54.self_attn.v_proj.bias",
+      "model.layers.55.input_layernorm",
+      "model.layers.55.mlp.gate",
+      "model.layers.55.mlp.shared_expert_gate",
+      "model.layers.55.post_attention_layernorm",
+      "model.layers.55.self_attn.k_proj.bias",
+      "model.layers.55.self_attn.q_proj.bias",
+      "model.layers.55.self_attn.v_proj.bias",
+      "model.layers.56.input_layernorm",
+      "model.layers.56.mlp.gate",
+      "model.layers.56.mlp.shared_expert_gate",
+      "model.layers.56.post_attention_layernorm",
+      "model.layers.56.self_attn.k_proj.bias",
+      "model.layers.56.self_attn.q_proj.bias",
+      "model.layers.56.self_attn.v_proj.bias",
+      "model.layers.57.input_layernorm",
+      "model.layers.57.mlp.gate",
+      "model.layers.57.mlp.shared_expert_gate",
+      "model.layers.57.post_attention_layernorm",
+      "model.layers.57.self_attn.k_proj.bias",
+      "model.layers.57.self_attn.q_proj.bias",
+      "model.layers.57.self_attn.v_proj.bias",
+      "model.layers.58.input_layernorm",
+      "model.layers.58.mlp.gate",
+      "model.layers.58.mlp.shared_expert_gate",
+      "model.layers.58.post_attention_layernorm",
+      "model.layers.58.self_attn.k_proj.bias",
+      "model.layers.58.self_attn.q_proj.bias",
+      "model.layers.58.self_attn.v_proj.bias",
+      "model.layers.59.input_layernorm",
+      "model.layers.59.mlp.gate",
+      "model.layers.59.mlp.shared_expert_gate",
+      "model.layers.59.post_attention_layernorm",
+      "model.layers.59.self_attn.k_proj.bias",
+      "model.layers.59.self_attn.q_proj.bias",
+      "model.layers.59.self_attn.v_proj.bias",
+      "model.layers.60.input_layernorm",
+      "model.layers.60.mlp.gate",
+      "model.layers.60.mlp.shared_expert_gate",
+      "model.layers.60.post_attention_layernorm",
+      "model.layers.60.self_attn.k_proj.bias",
+      "model.layers.60.self_attn.q_proj.bias",
+      "model.layers.60.self_attn.v_proj.bias",
+      "model.layers.61.input_layernorm",
+      "model.layers.61.mlp.gate",
+      "model.layers.61.mlp.shared_expert_gate",
+      "model.layers.61.post_attention_layernorm",
+      "model.layers.61.self_attn.k_proj.bias",
+      "model.layers.61.self_attn.q_proj.bias",
+      "model.layers.61.self_attn.v_proj.bias",
+      "model.layers.62.input_layernorm",
+      "model.layers.62.mlp.gate",
+      "model.layers.62.mlp.shared_expert_gate",
+      "model.layers.62.post_attention_layernorm",
+      "model.layers.62.self_attn.k_proj.bias",
+      "model.layers.62.self_attn.q_proj.bias",
+      "model.layers.62.self_attn.v_proj.bias",
+      "model.layers.63.input_layernorm",
+      "model.layers.63.mlp.gate",
+      "model.layers.63.mlp.shared_expert_gate",
+      "model.layers.63.post_attention_layernorm",
+      "model.layers.63.self_attn.k_proj.bias",
+      "model.layers.63.self_attn.q_proj.bias",
+      "model.layers.63.self_attn.v_proj.bias",
+      "model.layers.64.input_layernorm",
+      "model.layers.64.mlp.gate",
+      "model.layers.64.mlp.shared_expert_gate",
+      "model.layers.64.post_attention_layernorm",
+      "model.layers.64.self_attn.k_proj.bias",
+      "model.layers.64.self_attn.q_proj.bias",
+      "model.layers.64.self_attn.v_proj.bias",
+      "model.layers.65.input_layernorm",
+      "model.layers.65.mlp.gate",
+      "model.layers.65.mlp.shared_expert_gate",
+      "model.layers.65.post_attention_layernorm",
+      "model.layers.65.self_attn.k_proj.bias",
+      "model.layers.65.self_attn.q_proj.bias",
+      "model.layers.65.self_attn.v_proj.bias",
+      "model.layers.66.input_layernorm",
+      "model.layers.66.mlp.gate",
+      "model.layers.66.mlp.shared_expert_gate",
+      "model.layers.66.post_attention_layernorm",
+      "model.layers.66.self_attn.k_proj.bias",
+      "model.layers.66.self_attn.q_proj.bias",
+      "model.layers.66.self_attn.v_proj.bias",
+      "model.layers.67.input_layernorm",
+      "model.layers.67.mlp.gate",
+      "model.layers.67.mlp.shared_expert_gate",
+      "model.layers.67.post_attention_layernorm",
+      "model.layers.67.self_attn.k_proj.bias",
+      "model.layers.67.self_attn.q_proj.bias",
+      "model.layers.67.self_attn.v_proj.bias",
+      "model.layers.68.input_layernorm",
+      "model.layers.68.mlp.gate",
+      "model.layers.68.mlp.shared_expert_gate",
+      "model.layers.68.post_attention_layernorm",
+      "model.layers.68.self_attn.k_proj.bias",
+      "model.layers.68.self_attn.q_proj.bias",
+      "model.layers.68.self_attn.v_proj.bias",
+      "model.layers.69.input_layernorm",
+      "model.layers.69.mlp.gate",
+      "model.layers.69.mlp.shared_expert_gate",
+      "model.layers.69.post_attention_layernorm",
+      "model.layers.69.self_attn.k_proj.bias",
+      "model.layers.69.self_attn.q_proj.bias",
+      "model.layers.69.self_attn.v_proj.bias",
+      "model.layers.70.input_layernorm",
+      "model.layers.70.mlp.gate",
+      "model.layers.70.mlp.shared_expert_gate",
+      "model.layers.70.post_attention_layernorm",
+      "model.layers.70.self_attn.k_proj.bias",
+      "model.layers.70.self_attn.q_proj.bias",
+      "model.layers.70.self_attn.v_proj.bias",
+      "model.layers.71.input_layernorm",
+      "model.layers.71.mlp.gate",
+      "model.layers.71.mlp.shared_expert_gate",
+      "model.layers.71.post_attention_layernorm",
+      "model.layers.71.self_attn.k_proj.bias",
+      "model.layers.71.self_attn.q_proj.bias",
+      "model.layers.71.self_attn.v_proj.bias",
+      "model.layers.72.input_layernorm",
+      "model.layers.72.mlp.gate",
+      "model.layers.72.mlp.shared_expert_gate",
+      "model.layers.72.post_attention_layernorm",
+      "model.layers.72.self_attn.k_proj.bias",
+      "model.layers.72.self_attn.q_proj.bias",
+      "model.layers.72.self_attn.v_proj.bias",
+      "model.layers.73.input_layernorm",
+      "model.layers.73.mlp.gate",
+      "model.layers.73.mlp.shared_expert_gate",
+      "model.layers.73.post_attention_layernorm",
+      "model.layers.73.self_attn.k_proj.bias",
+      "model.layers.73.self_attn.q_proj.bias",
+      "model.layers.73.self_attn.v_proj.bias",
+      "model.layers.74.input_layernorm",
+      "model.layers.74.mlp.gate",
+      "model.layers.74.mlp.shared_expert_gate",
+      "model.layers.74.post_attention_layernorm",
+      "model.layers.74.self_attn.k_proj.bias",
+      "model.layers.74.self_attn.q_proj.bias",
+      "model.layers.74.self_attn.v_proj.bias",
+      "model.layers.75.input_layernorm",
+      "model.layers.75.mlp.gate",
+      "model.layers.75.mlp.shared_expert_gate",
+      "model.layers.75.post_attention_layernorm",
+      "model.layers.75.self_attn.k_proj.bias",
+      "model.layers.75.self_attn.q_proj.bias",
+      "model.layers.75.self_attn.v_proj.bias",
+      "model.layers.76.input_layernorm",
+      "model.layers.76.mlp.gate",
+      "model.layers.76.mlp.shared_expert_gate",
+      "model.layers.76.post_attention_layernorm",
+      "model.layers.76.self_attn.k_proj.bias",
+      "model.layers.76.self_attn.q_proj.bias",
+      "model.layers.76.self_attn.v_proj.bias",
+      "model.layers.77.input_layernorm",
+      "model.layers.77.mlp.gate",
+      "model.layers.77.mlp.shared_expert_gate",
+      "model.layers.77.post_attention_layernorm",
+      "model.layers.77.self_attn.k_proj.bias",
+      "model.layers.77.self_attn.q_proj.bias",
+      "model.layers.77.self_attn.v_proj.bias",
+      "model.layers.78.input_layernorm",
+      "model.layers.78.mlp.gate",
+      "model.layers.78.mlp.shared_expert_gate",
+      "model.layers.78.post_attention_layernorm",
+      "model.layers.78.self_attn.k_proj.bias",
+      "model.layers.78.self_attn.q_proj.bias",
+      "model.layers.78.self_attn.v_proj.bias",
+      "model.layers.79.input_layernorm",
+      "model.layers.79.mlp.gate",
+      "model.layers.79.mlp.shared_expert_gate",
+      "model.layers.79.post_attention_layernorm",
+      "model.layers.79.self_attn.k_proj.bias",
+      "model.layers.79.self_attn.q_proj.bias",
+      "model.layers.79.self_attn.v_proj.bias",
+      "model.layers.80.input_layernorm",
+      "model.layers.80.mlp.gate",
+      "model.layers.80.mlp.shared_expert_gate",
+      "model.layers.80.post_attention_layernorm",
+      "model.layers.80.self_attn.k_proj.bias",
+      "model.layers.80.self_attn.q_proj.bias",
+      "model.layers.80.self_attn.v_proj.bias",
+      "model.layers.81.input_layernorm",
+      "model.layers.81.mlp.gate",
+      "model.layers.81.mlp.shared_expert_gate",
+      "model.layers.81.post_attention_layernorm",
+      "model.layers.81.self_attn.k_proj.bias",
+      "model.layers.81.self_attn.q_proj.bias",
+      "model.layers.81.self_attn.v_proj.bias",
+      "model.layers.82.input_layernorm",
+      "model.layers.82.mlp.gate",
+      "model.layers.82.mlp.shared_expert_gate",
+      "model.layers.82.post_attention_layernorm",
+      "model.layers.82.self_attn.k_proj.bias",
+      "model.layers.82.self_attn.q_proj.bias",
+      "model.layers.82.self_attn.v_proj.bias",
+      "model.layers.83.input_layernorm",
+      "model.layers.83.mlp.gate",
+      "model.layers.83.mlp.shared_expert_gate",
+      "model.layers.83.post_attention_layernorm",
+      "model.layers.83.self_attn.k_proj.bias",
+      "model.layers.83.self_attn.q_proj.bias",
+      "model.layers.83.self_attn.v_proj.bias",
+      "model.layers.84.input_layernorm",
+      "model.layers.84.mlp.gate",
+      "model.layers.84.mlp.shared_expert_gate",
+      "model.layers.84.post_attention_layernorm",
+      "model.layers.84.self_attn.k_proj.bias",
+      "model.layers.84.self_attn.q_proj.bias",
+      "model.layers.84.self_attn.v_proj.bias",
+      "model.layers.85.input_layernorm",
+      "model.layers.85.mlp.gate",
+      "model.layers.85.mlp.shared_expert_gate",
+      "model.layers.85.post_attention_layernorm",
+      "model.layers.85.self_attn.k_proj.bias",
+      "model.layers.85.self_attn.q_proj.bias",
+      "model.layers.85.self_attn.v_proj.bias",
+      "model.layers.86.input_layernorm",
+      "model.layers.86.mlp.gate",
+      "model.layers.86.mlp.shared_expert_gate",
+      "model.layers.86.post_attention_layernorm",
+      "model.layers.86.self_attn.k_proj.bias",
+      "model.layers.86.self_attn.q_proj.bias",
+      "model.layers.86.self_attn.v_proj.bias",
+      "model.layers.87.input_layernorm",
+      "model.layers.87.mlp.gate",
+      "model.layers.87.mlp.shared_expert_gate",
+      "model.layers.87.post_attention_layernorm",
+      "model.layers.87.self_attn.k_proj.bias",
+      "model.layers.87.self_attn.q_proj.bias",
+      "model.layers.87.self_attn.v_proj.bias",
+      "model.layers.88.input_layernorm",
+      "model.layers.88.mlp.gate",
+      "model.layers.88.mlp.shared_expert_gate",
+      "model.layers.88.post_attention_layernorm",
+      "model.layers.88.self_attn.k_proj.bias",
+      "model.layers.88.self_attn.q_proj.bias",
+      "model.layers.88.self_attn.v_proj.bias",
+      "model.layers.89.input_layernorm",
+      "model.layers.89.mlp.gate",
+      "model.layers.89.mlp.shared_expert_gate",
+      "model.layers.89.post_attention_layernorm",
+      "model.layers.89.self_attn.k_proj.bias",
+      "model.layers.89.self_attn.q_proj.bias",
+      "model.layers.89.self_attn.v_proj.bias",
+      "model.layers.90.input_layernorm",
+      "model.layers.90.mlp.gate",
+      "model.layers.90.mlp.shared_expert_gate",
+      "model.layers.90.post_attention_layernorm",
+      "model.layers.90.self_attn.k_proj.bias",
+      "model.layers.90.self_attn.q_proj.bias",
+      "model.layers.90.self_attn.v_proj.bias",
+      "model.layers.91.input_layernorm",
+      "model.layers.91.mlp.gate",
+      "model.layers.91.mlp.shared_expert_gate",
+      "model.layers.91.post_attention_layernorm",
+      "model.layers.91.self_attn.k_proj.bias",
+      "model.layers.91.self_attn.q_proj.bias",
+      "model.layers.91.self_attn.v_proj.bias",
+      "model.layers.92.input_layernorm",
+      "model.layers.92.mlp.gate",
+      "model.layers.92.mlp.shared_expert_gate",
+      "model.layers.92.post_attention_layernorm",
+      "model.layers.92.self_attn.k_proj.bias",
+      "model.layers.92.self_attn.q_proj.bias",
+      "model.layers.92.self_attn.v_proj.bias",
+      "model.layers.93.input_layernorm",
+      "model.layers.93.mlp.gate",
+      "model.layers.93.mlp.shared_expert_gate",
+      "model.layers.93.post_attention_layernorm",
+      "model.layers.93.self_attn.k_proj.bias",
+      "model.layers.93.self_attn.q_proj.bias",
+      "model.layers.93.self_attn.v_proj.bias",
+      "lm_head",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.mlp.gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.mlp.gate",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.gate",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.gate",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.gate",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.gate",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.gate",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.gate",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.gate",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.gate",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.gate",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.k_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.gate",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.gate",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.gate",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.gate",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.23.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.gate",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.gate",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.gate",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.gate",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.28.mlp.shared_expert_gate",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.gate",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.gate",
+      "model.layers.29.mlp.shared_expert_gate",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.29.self_attn.v_proj.bias",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.gate",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.30.mlp.shared_expert_gate",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.gate",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.31.mlp.shared_expert_gate",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.gate",
+      "model.layers.32.mlp.shared_expert_gate",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.gate",
+      "model.layers.33.mlp.shared_expert_gate",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.gate",
+      "model.layers.34.mlp.shared_expert_gate",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.gate",
+      "model.layers.35.mlp.shared_expert_gate",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.gate",
+      "model.layers.36.mlp.shared_expert_gate",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.gate",
+      "model.layers.37.mlp.shared_expert_gate",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.gate",
+      "model.layers.38.mlp.shared_expert_gate",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.gate",
+      "model.layers.39.mlp.shared_expert_gate",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.k_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.gate",
+      "model.layers.40.mlp.shared_expert_gate",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.gate",
+      "model.layers.41.mlp.shared_expert_gate",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.gate",
+      "model.layers.42.mlp.shared_expert_gate",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.gate",
+      "model.layers.43.mlp.shared_expert_gate",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.gate",
+      "model.layers.44.mlp.shared_expert_gate",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.gate",
+      "model.layers.45.mlp.shared_expert_gate",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.v_proj.bias",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.gate",
+      "model.layers.46.mlp.shared_expert_gate",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.k_proj.bias",
+      "model.layers.46.self_attn.q_proj.bias",
+      "model.layers.46.self_attn.v_proj.bias",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.gate",
+      "model.layers.47.mlp.shared_expert_gate",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.k_proj.bias",
+      "model.layers.47.self_attn.q_proj.bias",
+      "model.layers.47.self_attn.v_proj.bias",
+      "model.layers.48.input_layernorm",
+      "model.layers.48.mlp.gate",
+      "model.layers.48.mlp.shared_expert_gate",
+      "model.layers.48.post_attention_layernorm",
+      "model.layers.48.self_attn.k_proj.bias",
+      "model.layers.48.self_attn.q_proj.bias",
+      "model.layers.48.self_attn.v_proj.bias",
+      "model.layers.49.input_layernorm",
+      "model.layers.49.mlp.gate",
+      "model.layers.49.mlp.shared_expert_gate",
+      "model.layers.49.post_attention_layernorm",
+      "model.layers.49.self_attn.k_proj.bias",
+      "model.layers.49.self_attn.q_proj.bias",
+      "model.layers.49.self_attn.v_proj.bias",
+      "model.layers.50.input_layernorm",
+      "model.layers.50.mlp.gate",
+      "model.layers.50.mlp.shared_expert_gate",
+      "model.layers.50.post_attention_layernorm",
+      "model.layers.50.self_attn.k_proj.bias",
+      "model.layers.50.self_attn.q_proj.bias",
+      "model.layers.50.self_attn.v_proj.bias",
+      "model.layers.51.input_layernorm",
+      "model.layers.51.mlp.gate",
+      "model.layers.51.mlp.shared_expert_gate",
+      "model.layers.51.post_attention_layernorm",
+      "model.layers.51.self_attn.k_proj.bias",
+      "model.layers.51.self_attn.q_proj.bias",
+      "model.layers.51.self_attn.v_proj.bias",
+      "model.layers.52.input_layernorm",
+      "model.layers.52.mlp.gate",
+      "model.layers.52.mlp.shared_expert_gate",
+      "model.layers.52.post_attention_layernorm",
+      "model.layers.52.self_attn.k_proj.bias",
+      "model.layers.52.self_attn.q_proj.bias",
+      "model.layers.52.self_attn.v_proj.bias",
+      "model.layers.53.input_layernorm",
+      "model.layers.53.mlp.gate",
+      "model.layers.53.mlp.shared_expert_gate",
+      "model.layers.53.post_attention_layernorm",
+      "model.layers.53.self_attn.k_proj.bias",
+      "model.layers.53.self_attn.q_proj.bias",
+      "model.layers.53.self_attn.v_proj.bias",
+      "model.layers.54.input_layernorm",
+      "model.layers.54.mlp.gate",
+      "model.layers.54.mlp.shared_expert_gate",
+      "model.layers.54.post_attention_layernorm",
+      "model.layers.54.self_attn.k_proj.bias",
+      "model.layers.54.self_attn.q_proj.bias",
+      "model.layers.54.self_attn.v_proj.bias",
+      "model.layers.55.input_layernorm",
+      "model.layers.55.mlp.gate",
+      "model.layers.55.mlp.shared_expert_gate",
+      "model.layers.55.post_attention_layernorm",
+      "model.layers.55.self_attn.k_proj.bias",
+      "model.layers.55.self_attn.q_proj.bias",
+      "model.layers.55.self_attn.v_proj.bias",
+      "model.layers.56.input_layernorm",
+      "model.layers.56.mlp.gate",
+      "model.layers.56.mlp.shared_expert_gate",
+      "model.layers.56.post_attention_layernorm",
+      "model.layers.56.self_attn.k_proj.bias",
+      "model.layers.56.self_attn.q_proj.bias",
+      "model.layers.56.self_attn.v_proj.bias",
+      "model.layers.57.input_layernorm",
+      "model.layers.57.mlp.gate",
+      "model.layers.57.mlp.shared_expert_gate",
+      "model.layers.57.post_attention_layernorm",
+      "model.layers.57.self_attn.k_proj.bias",
+      "model.layers.57.self_attn.q_proj.bias",
+      "model.layers.57.self_attn.v_proj.bias",
+      "model.layers.58.input_layernorm",
+      "model.layers.58.mlp.gate",
+      "model.layers.58.mlp.shared_expert_gate",
+      "model.layers.58.post_attention_layernorm",
+      "model.layers.58.self_attn.k_proj.bias",
+      "model.layers.58.self_attn.q_proj.bias",
+      "model.layers.58.self_attn.v_proj.bias",
+      "model.layers.59.input_layernorm",
+      "model.layers.59.mlp.gate",
+      "model.layers.59.mlp.shared_expert_gate",
+      "model.layers.59.post_attention_layernorm",
+      "model.layers.59.self_attn.k_proj.bias",
+      "model.layers.59.self_attn.q_proj.bias",
+      "model.layers.59.self_attn.v_proj.bias",
+      "model.layers.60.input_layernorm",
+      "model.layers.60.mlp.gate",
+      "model.layers.60.mlp.shared_expert_gate",
+      "model.layers.60.post_attention_layernorm",
+      "model.layers.60.self_attn.k_proj.bias",
+      "model.layers.60.self_attn.q_proj.bias",
+      "model.layers.60.self_attn.v_proj.bias",
+      "model.layers.61.input_layernorm",
+      "model.layers.61.mlp.gate",
+      "model.layers.61.mlp.shared_expert_gate",
+      "model.layers.61.post_attention_layernorm",
+      "model.layers.61.self_attn.k_proj.bias",
+      "model.layers.61.self_attn.q_proj.bias",
+      "model.layers.61.self_attn.v_proj.bias",
+      "model.layers.62.input_layernorm",
+      "model.layers.62.mlp.gate",
+      "model.layers.62.mlp.shared_expert_gate",
+      "model.layers.62.post_attention_layernorm",
+      "model.layers.62.self_attn.k_proj.bias",
+      "model.layers.62.self_attn.q_proj.bias",
+      "model.layers.62.self_attn.v_proj.bias",
+      "model.layers.63.input_layernorm",
+      "model.layers.63.mlp.gate",
+      "model.layers.63.mlp.shared_expert_gate",
+      "model.layers.63.post_attention_layernorm",
+      "model.layers.63.self_attn.k_proj.bias",
+      "model.layers.63.self_attn.q_proj.bias",
+      "model.layers.63.self_attn.v_proj.bias",
+      "model.layers.64.input_layernorm",
+      "model.layers.64.mlp.gate",
+      "model.layers.64.mlp.shared_expert_gate",
+      "model.layers.64.post_attention_layernorm",
+      "model.layers.64.self_attn.k_proj.bias",
+      "model.layers.64.self_attn.q_proj.bias",
+      "model.layers.64.self_attn.v_proj.bias",
+      "model.layers.65.input_layernorm",
+      "model.layers.65.mlp.gate",
+      "model.layers.65.mlp.shared_expert_gate",
+      "model.layers.65.post_attention_layernorm",
+      "model.layers.65.self_attn.k_proj.bias",
+      "model.layers.65.self_attn.q_proj.bias",
+      "model.layers.65.self_attn.v_proj.bias",
+      "model.layers.66.input_layernorm",
+      "model.layers.66.mlp.gate",
+      "model.layers.66.mlp.shared_expert_gate",
+      "model.layers.66.post_attention_layernorm",
+      "model.layers.66.self_attn.k_proj.bias",
+      "model.layers.66.self_attn.q_proj.bias",
+      "model.layers.66.self_attn.v_proj.bias",
+      "model.layers.67.input_layernorm",
+      "model.layers.67.mlp.gate",
+      "model.layers.67.mlp.shared_expert_gate",
+      "model.layers.67.post_attention_layernorm",
+      "model.layers.67.self_attn.k_proj.bias",
+      "model.layers.67.self_attn.q_proj.bias",
+      "model.layers.67.self_attn.v_proj.bias",
+      "model.layers.68.input_layernorm",
+      "model.layers.68.mlp.gate",
+      "model.layers.68.mlp.shared_expert_gate",
+      "model.layers.68.post_attention_layernorm",
+      "model.layers.68.self_attn.k_proj.bias",
+      "model.layers.68.self_attn.q_proj.bias",
+      "model.layers.68.self_attn.v_proj.bias",
+      "model.layers.69.input_layernorm",
+      "model.layers.69.mlp.gate",
+      "model.layers.69.mlp.shared_expert_gate",
+      "model.layers.69.post_attention_layernorm",
+      "model.layers.69.self_attn.k_proj.bias",
+      "model.layers.69.self_attn.q_proj.bias",
+      "model.layers.69.self_attn.v_proj.bias",
+      "model.layers.70.input_layernorm",
+      "model.layers.70.mlp.gate",
+      "model.layers.70.mlp.shared_expert_gate",
+      "model.layers.70.post_attention_layernorm",
+      "model.layers.70.self_attn.k_proj.bias",
+      "model.layers.70.self_attn.q_proj.bias",
+      "model.layers.70.self_attn.v_proj.bias",
+      "model.layers.71.input_layernorm",
+      "model.layers.71.mlp.gate",
+      "model.layers.71.mlp.shared_expert_gate",
+      "model.layers.71.post_attention_layernorm",
+      "model.layers.71.self_attn.k_proj.bias",
+      "model.layers.71.self_attn.q_proj.bias",
+      "model.layers.71.self_attn.v_proj.bias",
+      "model.layers.72.input_layernorm",
+      "model.layers.72.mlp.gate",
+      "model.layers.72.mlp.shared_expert_gate",
+      "model.layers.72.post_attention_layernorm",
+      "model.layers.72.self_attn.k_proj.bias",
+      "model.layers.72.self_attn.q_proj.bias",
+      "model.layers.72.self_attn.v_proj.bias",
+      "model.layers.73.input_layernorm",
+      "model.layers.73.mlp.gate",
+      "model.layers.73.mlp.shared_expert_gate",
+      "model.layers.73.post_attention_layernorm",
+      "model.layers.73.self_attn.k_proj.bias",
+      "model.layers.73.self_attn.q_proj.bias",
+      "model.layers.73.self_attn.v_proj.bias",
+      "model.layers.74.input_layernorm",
+      "model.layers.74.mlp.gate",
+      "model.layers.74.mlp.shared_expert_gate",
+      "model.layers.74.post_attention_layernorm",
+      "model.layers.74.self_attn.k_proj.bias",
+      "model.layers.74.self_attn.q_proj.bias",
+      "model.layers.74.self_attn.v_proj.bias",
+      "model.layers.75.input_layernorm",
+      "model.layers.75.mlp.gate",
+      "model.layers.75.mlp.shared_expert_gate",
+      "model.layers.75.post_attention_layernorm",
+      "model.layers.75.self_attn.k_proj.bias",
+      "model.layers.75.self_attn.q_proj.bias",
+      "model.layers.75.self_attn.v_proj.bias",
+      "model.layers.76.input_layernorm",
+      "model.layers.76.mlp.gate",
+      "model.layers.76.mlp.shared_expert_gate",
+      "model.layers.76.post_attention_layernorm",
+      "model.layers.76.self_attn.k_proj.bias",
+      "model.layers.76.self_attn.q_proj.bias",
+      "model.layers.76.self_attn.v_proj.bias",
+      "model.layers.77.input_layernorm",
+      "model.layers.77.mlp.gate",
+      "model.layers.77.mlp.shared_expert_gate",
+      "model.layers.77.post_attention_layernorm",
+      "model.layers.77.self_attn.k_proj.bias",
+      "model.layers.77.self_attn.q_proj.bias",
+      "model.layers.77.self_attn.v_proj.bias",
+      "model.layers.78.input_layernorm",
+      "model.layers.78.mlp.gate",
+      "model.layers.78.mlp.shared_expert_gate",
+      "model.layers.78.post_attention_layernorm",
+      "model.layers.78.self_attn.k_proj.bias",
+      "model.layers.78.self_attn.q_proj.bias",
+      "model.layers.78.self_attn.v_proj.bias",
+      "model.layers.79.input_layernorm",
+      "model.layers.79.mlp.gate",
+      "model.layers.79.mlp.shared_expert_gate",
+      "model.layers.79.post_attention_layernorm",
+      "model.layers.79.self_attn.k_proj.bias",
+      "model.layers.79.self_attn.q_proj.bias",
+      "model.layers.79.self_attn.v_proj.bias",
+      "model.layers.80.input_layernorm",
+      "model.layers.80.mlp.gate",
+      "model.layers.80.mlp.shared_expert_gate",
+      "model.layers.80.post_attention_layernorm",
+      "model.layers.80.self_attn.k_proj.bias",
+      "model.layers.80.self_attn.q_proj.bias",
+      "model.layers.80.self_attn.v_proj.bias",
+      "model.layers.81.input_layernorm",
+      "model.layers.81.mlp.gate",
+      "model.layers.81.mlp.shared_expert_gate",
+      "model.layers.81.post_attention_layernorm",
+      "model.layers.81.self_attn.k_proj.bias",
+      "model.layers.81.self_attn.q_proj.bias",
+      "model.layers.81.self_attn.v_proj.bias",
+      "model.layers.82.input_layernorm",
+      "model.layers.82.mlp.gate",
+      "model.layers.82.mlp.shared_expert_gate",
+      "model.layers.82.post_attention_layernorm",
+      "model.layers.82.self_attn.k_proj.bias",
+      "model.layers.82.self_attn.q_proj.bias",
+      "model.layers.82.self_attn.v_proj.bias",
+      "model.layers.83.input_layernorm",
+      "model.layers.83.mlp.gate",
+      "model.layers.83.mlp.shared_expert_gate",
+      "model.layers.83.post_attention_layernorm",
+      "model.layers.83.self_attn.k_proj.bias",
+      "model.layers.83.self_attn.q_proj.bias",
+      "model.layers.83.self_attn.v_proj.bias",
+      "model.layers.84.input_layernorm",
+      "model.layers.84.mlp.gate",
+      "model.layers.84.mlp.shared_expert_gate",
+      "model.layers.84.post_attention_layernorm",
+      "model.layers.84.self_attn.k_proj.bias",
+      "model.layers.84.self_attn.q_proj.bias",
+      "model.layers.84.self_attn.v_proj.bias",
+      "model.layers.85.input_layernorm",
+      "model.layers.85.mlp.gate",
+      "model.layers.85.mlp.shared_expert_gate",
+      "model.layers.85.post_attention_layernorm",
+      "model.layers.85.self_attn.k_proj.bias",
+      "model.layers.85.self_attn.q_proj.bias",
+      "model.layers.85.self_attn.v_proj.bias",
+      "model.layers.86.input_layernorm",
+      "model.layers.86.mlp.gate",
+      "model.layers.86.mlp.shared_expert_gate",
+      "model.layers.86.post_attention_layernorm",
+      "model.layers.86.self_attn.k_proj.bias",
+      "model.layers.86.self_attn.q_proj.bias",
+      "model.layers.86.self_attn.v_proj.bias",
+      "model.layers.87.input_layernorm",
+      "model.layers.87.mlp.gate",
+      "model.layers.87.mlp.shared_expert_gate",
+      "model.layers.87.post_attention_layernorm",
+      "model.layers.87.self_attn.k_proj.bias",
+      "model.layers.87.self_attn.q_proj.bias",
+      "model.layers.87.self_attn.v_proj.bias",
+      "model.layers.88.input_layernorm",
+      "model.layers.88.mlp.gate",
+      "model.layers.88.mlp.shared_expert_gate",
+      "model.layers.88.post_attention_layernorm",
+      "model.layers.88.self_attn.k_proj.bias",
+      "model.layers.88.self_attn.q_proj.bias",
+      "model.layers.88.self_attn.v_proj.bias",
+      "model.layers.89.input_layernorm",
+      "model.layers.89.mlp.gate",
+      "model.layers.89.mlp.shared_expert_gate",
+      "model.layers.89.post_attention_layernorm",
+      "model.layers.89.self_attn.k_proj.bias",
+      "model.layers.89.self_attn.q_proj.bias",
+      "model.layers.89.self_attn.v_proj.bias",
+      "model.layers.90.input_layernorm",
+      "model.layers.90.mlp.gate",
+      "model.layers.90.mlp.shared_expert_gate",
+      "model.layers.90.post_attention_layernorm",
+      "model.layers.90.self_attn.k_proj.bias",
+      "model.layers.90.self_attn.q_proj.bias",
+      "model.layers.90.self_attn.v_proj.bias",
+      "model.layers.91.input_layernorm",
+      "model.layers.91.mlp.gate",
+      "model.layers.91.mlp.shared_expert_gate",
+      "model.layers.91.post_attention_layernorm",
+      "model.layers.91.self_attn.k_proj.bias",
+      "model.layers.91.self_attn.q_proj.bias",
+      "model.layers.91.self_attn.v_proj.bias",
+      "model.layers.92.input_layernorm",
+      "model.layers.92.mlp.gate",
+      "model.layers.92.mlp.shared_expert_gate",
+      "model.layers.92.post_attention_layernorm",
+      "model.layers.92.self_attn.k_proj.bias",
+      "model.layers.92.self_attn.q_proj.bias",
+      "model.layers.92.self_attn.v_proj.bias",
+      "model.layers.93.input_layernorm",
+      "model.layers.93.mlp.gate",
+      "model.layers.93.mlp.shared_expert_gate",
+      "model.layers.93.post_attention_layernorm",
+      "model.layers.93.self_attn.k_proj.bias",
+      "model.layers.93.self_attn.q_proj.bias",
+      "model.layers.93.self_attn.v_proj.bias"
+    ],
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706bdca89212f2133e635ca3efdb90b60a416f692690b8021243c84a21c3d3d3
+size 4979380200

model-00002-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1d1f11da42959546b9dcf2cfbb08dcb3cac9fa97b282bfa33641ed1902ca0f
+size 4980115368

model-00003-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66099ae2431032cb77af21de7d6ca79042c9453146a405393c60c0a9cd26438
+size 4980115368

model-00004-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51edb8421bd34467dac2b9d866f17f8675ebc4f1122ff74ca02ac682427f7a7
+size 4980115368

model-00005-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa4fcbc7b569cdbb06a021c937f2dba7595897129073f0b68ce796c00d9f560
+size 4980115368

model-00006-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccb02367969b5dd24c27c613ded7bdd1144a8502e17220c6744e3162fb1927f
+size 4980116144

model-00007-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70aad7fffad43a2b2dbe6e473de09c8e27e5b398525bd15b7533080f9a68603b
+size 4980116928

model-00008-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e3e3bd9c46fc2700119442e3d26e77e3901cc153345f64ae68c650a67009c4
+size 4980116928

model-00009-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec95962dcceb0cecadd685371f267066d51143f5107785689eb99026f5efacb2
+size 4980116928

model-00010-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad89ee9294c0bef673dce5984bdc241d07157f4e663917c6d3fd1b1b87bee557
+size 4980116928

model-00011-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69e3447252ee95c705d6672958efda08350ade577c93f11167c5fdea3799d1d
+size 4980116928

model-00012-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f70249a89ed7e0f52b0cbb39d6399a2d270a0a1b25540ee18ab9700e8432cc6
+size 4980116928

model-00013-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55608cd7bc0925336949d8c3182f237a08055df419660147eec5db37610545c9
+size 4980116928

model-00014-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f4686c94b0e70a93fd8c4be56ae03436401be5051f412df566c035032130f9
+size 4980116928

model-00015-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd1fd1f52cee3b267947712b833ee6c9f97eb115407bc9c13ccb2847d311f4a
+size 4980116928

model-00016-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab658449c6be471fe4830d66be5e5dd89414c8bf58feb11eda1ea2f2ab973ab4
+size 4980116928

model-00017-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929d66a5ce3e4cc6c8b4e6c3ac82007a9ca2df3086b341e4c8042e591c937ad3
+size 4980116928

model-00018-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd40a8052900d27f9fdf706b2b38fbeb2071d90183810d998f974bcbc8c64d0f
+size 4980116928

model-00019-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983ac915e42520874e4badf1042320db547da3fcae4dbfbeb7e43b148bb2ebe7
+size 4980116928

model-00020-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8d4f9527d3610c95e4603d7280fe849619e19c9455d731bab25602b82727f7
+size 4980116928

model-00021-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37514d95e9a3cfb4b95d50e5683f1a406c17082a8cd95f3f6d4cb33e492b7b99
+size 4980116928

model-00022-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6229a37f428583e43e2ceb198937d792ac0aefb0686977f84a7e3a4867c8d27
+size 4980116928

model-00023-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b149a81ddb47fbaf91f365d3087124bdf1a665a33bff98f872b7014d5587d89
+size 4980116928

model-00024-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1affab458b58aca4d4cc1f830ac100c99e772dc6008e138c7e89a5e737fcf3
+size 4980116928

model-00025-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949a250c15dc286f816cd4c56bc0ede743dca7d2c9dccfee79d9f9f380537bd2
+size 4980116928

model-00026-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f8e70666d3c8805b4ebbadc91c511283aac5c3eb1e1fb44b5ac1b394c139d6
+size 4980116928

model-00027-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea3b6a41961059d652860b04cd2d309e7717cebb9fe28404bff760c65608a32
+size 4980116928

model-00028-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953f9986188b15d3ecfb6b556a7baeb33dbf89f92d686c9e9386d490e5c57230
+size 4980116928

model-00029-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308b29d78c654c7b13d2cb99588433d45fefd4d9442d5dabbe38363c5507de17
+size 4980116928

model-00030-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c940f6f57838619d6e371ac8b2ffbbd5818e3c17c60d864c438857fe945c15ab
+size 4980116928

model-00031-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac276a11c01013803eefa18ef4e4dd8ab68c85403d3b0f2c1db070bee321f31
+size 4980116928

model-00032-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd39816214bba9965221f9ee2c6d5acaadf74661b7293b6db4f73adc84e45783
+size 4980116928

model-00033-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f897a502ea497486c2e53e401c4b55b0cf4bdd12368cefb84206273ef4d9834d
+size 4980116928

model-00034-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f62c0011ef371aaa7f6a2c0c685c6198181595b85d88dc53a4ace11ae00762
+size 4980116928

model-00035-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0afd80b55deae16ed9da2ee4683e0aaa8788be1c6bd998f77520d1fc263fda
+size 4980116928

model-00036-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d164ede9c910a6b3197fa0ac7b25530f1729da657ad4b745946b654730c876b
+size 4980116928

model-00037-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c3b62e295946c09d59fd79b67b513c505404b9cff1f1704e4f4223c7a3a748
+size 4980116928

model-00038-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4151f5d2a37e0218654ebd005966b4f6362da883a5891a6f6904d068d590718a
+size 4980116928

model-00039-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d0dc282ebcc65abff567a11121ec7cbb47ad258c2333e1b41895927341ad30
+size 4980116928

model-00040-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d4a65df150f54dd548b2a3d7e4a30a21c699e40443b27819a4af4a1c6fa8cf
+size 4980116928

model-00041-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a28cdb6c9ac79933995e5071830cab4b53980c94ec506a8b42b57b40fbf9a7
+size 4980116928

model-00042-of-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb17200b61465957778971063142c312f7c2c98c384ae0b3a4f964113d1a7396
+size 4980116928