Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "<|execute_end|>": 73444,
+  "<|execute_start|>": 73443,
+  "<|fim_middle|>": 73446,
+  "<|fim_prefix|>": 73445,
+  "<|fim_suffix|>": 73447,
+  "<|im_end|>": 73440,
+  "<|im_start|>": 73441,
+  "<|tool_call|>": 73442,
+  "[PAD]": 73448
+}

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "openbmb/MiniCPM3-4B",
+  "architectures": [
+    "MiniCPM3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "openbmb/MiniCPM3-4B--configuration_minicpm.MiniCPM3Config",
+    "AutoModel": "openbmb/MiniCPM3-4B--modeling_minicpm.MiniCPM3Model",
+    "AutoModelForCausalLM": "openbmb/MiniCPM3-4B--modeling_minicpm.MiniCPM3ForCausalLM",
+    "AutoModelForSeq2SeqLM": "openbmb/MiniCPM3-4B--modeling_minicpm.MiniCPM3ForCausalLM",
+    "AutoModelForSequenceClassification": "openbmb/MiniCPM3-4B--modeling_minicpm.MiniCPM3ForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "dim_model_base": 256,
+  "eos_token_id": [
+    2,
+    73440
+  ],
+  "head_dim": 96,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.1,
+  "intermediate_size": 6400,
+  "kv_lora_rank": 256,
+  "max_position_embeddings": 32768,
+  "model_type": "minicpm3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "q_lora_rank": 768,
+  "qk_nope_head_dim": 64,
+  "qk_rope_head_dim": 32,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0591234137867171,
+      1.1241891283591912,
+      1.2596935748670968,
+      1.5380380402321725,
+      2.093982484148734,
+      3.1446935121267696,
+      4.937952647693647,
+      7.524541999994549,
+      10.475458000005451,
+      13.062047352306353,
+      14.85530648787323,
+      15.906017515851266,
+      16.461961959767827,
+      16.740306425132907,
+      16.87581087164081,
+      16.940876586213285
+    ],
+    "original_max_position_embeddings": 32768,
+    "short_factor": [
+      1.0591234137867171,
+      1.1241891283591912,
+      1.2596935748670968,
+      1.5380380402321725,
+      2.093982484148734,
+      3.1446935121267696,
+      4.937952647693647,
+      7.524541999994549,
+      10.475458000005451,
+      13.062047352306353,
+      14.85530648787323,
+      15.906017515851266,
+      16.461961959767827,
+      16.740306425132907,
+      16.87581087164081,
+      16.940876586213285
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "scale_depth": 1.4,
+  "scale_emb": 12,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "v_head_dim": 64,
+  "vocab_size": 73448
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    73440
+  ],
+  "temperature": 0.8,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a134a9ce623081307282f4875c2fde941227424c6cbd60fbdeb8fd3c7c5ccd
+size 4981273024

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c7b5611ed6055aac90f0c908ee242a52b5dec10cee7fd1c0f27a4f8a0233dc
+size 3166566032

model.safetensors.index.json

@@ -0,0 +1,753 @@
+{
+  "metadata": {
+    "total_size": 8147751936
+  },
+  "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.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.32.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.33.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.34.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.35.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.kv_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.q_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.36.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.40.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.41.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.42.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.43.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.44.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.45.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.46.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.47.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.48.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.49.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.50.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.51.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.52.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.53.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.54.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.55.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.56.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.57.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.58.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.59.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.60.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.kv_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.kv_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.q_a_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.q_a_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.61.self_attn.q_b_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.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.kv_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.kv_b_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_a_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_a_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_b_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

retriever_documents.txt

@@ -0,0 +1,2 @@
+This is a sample document.
+Another sample document here.

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb74d51116831c3bf65db812c553f94ab0c88dcf97a5bbb37e3504f6d359c530
+size 1181204

tokenizer_config.json

@@ -0,0 +1,125 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73440": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73441": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73442": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73443": {
+      "content": "<|execute_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73444": {
+      "content": "<|execute_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73445": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73446": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73447": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73448": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>",
+    "<|tool_call|>",
+    "<|execute_start|>",
+    "<|execute_end|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{%- macro json_to_python_type(param_name, json_spec) %}\n{%- set basic_type_map = {\n  'string': 'str',\n  'number': 'float',\n  'integer': 'int',\n  'boolean': 'bool',\n  'null': 'None'\n} %}\n\n{%- if json_spec.enum %}\n  {{- param_name|title }}\n{%- elif basic_type_map[json_spec.type] is defined %}\n  {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == 'array' %}\n  {{- 'List[' +  json_to_python_type(param_name, json_spec['items']) + ']' }}\n{%- elif json_spec.type == 'object' %}\n  {{- 'Dict[str, ' + json_to_python_type(param_name, json_spec.additionalProperties if json_spec.additionalProperties else 'Any') + ']' if not json_spec.properties else param_name|title }}\n{%- elif json_spec.type is iterable %}\n  {{- 'Union[' }}\n  {%- for t in json_spec.type %}\n    {{- json_to_python_type(param_name, {'type': t}) }}\n    {{- ', ' if not loop.last }}\n  {%- endfor %}\n  {{- ']' }}\n{%- else %}\n  {{- 'Any' }}\n{%- endif %}\n{%- endmacro %}\n\n{%- macro object_to_fields(json_spec, field_indent) %}\n  {%- set o_ns = namespace(f = caller()) %}\n  {%- for param_name, param_fields in json_spec.properties|items %}\n    {%- if param_fields.enum %}\n      {{- '\\n\\nclass ' + param_name|title + '(Enum):\\n' }}\n      {%- for enum_option in param_fields.enum %}\n        {{- '    enum_' + loop.index0|string + ' = ' + enum_option|tojson + '\\n' }}\n      {%- endfor %}\n    {%- elif param_fields.type == 'object' and param_fields.properties %}\n      {%- call object_to_fields(param_fields, '    ') %}\n        {{- '\\n\\nclass ' + param_name|title + '(BaseModel):\\n' }}\n      {%- endcall %}\n    {%- elif param_fields.type == 'array' and param_fields['items'] and param_fields['items'].type == 'object' and param_fields['items'].properties %}\n      {%- call object_to_fields(param_fields['items'], '    ') %}\n        {{- '\\n\\nclass ' + param_name|title + '(BaseModel):\\n' }}\n      {%- endcall %}\n    {%- endif %}\n    {%- set param_default = param_fields.default|tojson if param_fields.default is string else param_fields.default|string if param_fields.default is defined else 'None' %}\n    {%- set o_ns.f = o_ns.f + field_indent + param_name + ': ' %}\n    {%- set o_ns.f = o_ns.f + ('Optional[' + json_to_python_type(param_name, param_fields) + ']' if param_name not in json_spec.required else json_to_python_type(param_name, param_fields)) %}\n    {%- if not param_fields.title and not param_fields.description and not param_fields.pattern %}\n      {%- set o_ns.f = o_ns.f + (' = ' + param_default if param_name not in json_spec.required else '') %}\n    {%- else %}\n      {%- set o_ns.f = o_ns.f + (' = Field(...' if param_name in json_spec.required else ' = Field(' + param_default) %}\n      {%- set o_ns.f = o_ns.f + (', description=' + param_fields.description|tojson if param_fields.description else '') %}\n      {%- set o_ns.f = o_ns.f + (', regex=' + param_fields.pattern|tojson if param_fields.pattern else '') %}\n      {%- set o_ns.f = o_ns.f + (', title=' + param_fields.title|tojson if param_fields.title else '') %}\n      {%- set o_ns.f = o_ns.f + ')' %}\n    {%- endif %}\n    {%- set o_ns.f = o_ns.f + '\\n' %}\n  {%- endfor %}\n  {{- o_ns.f }}\n{%- endmacro %}\n\n{%- macro tool_parser(tools) %}\n{%- for tool in tools %}\n  {%- if tool.type is not defined or tool.type == 'function' %}\n    {%- if tool.function is defined %}\n      {%- set tool = tool.function %}\n    {%- endif %}\n    {%- set tool_params = tool.parameters if tool.parameters is defined else none %}\n    {%- call object_to_fields(tool_params, '        ') %}\n      {{- '\\n\\ndef ' + tool.name + '(' }}\n      {%- if tool_params %}\n        {%- for param_name, param_fields in tool_params.properties|items %}\n          {%- set param_default = param_fields.default|tojson if param_fields.default is string else param_fields.default|string if param_fields.default is defined else 'None' %}\n          {{- ', ' if loop.index0 != 0 }}\n          {{- param_name }}\n          {{- '=' + param_default if param_name not in tool_params.required }}\n        {%- endfor %}\n      {%- endif %}\n      {{- '):\\n    \"\"\"' }}\n      {{- tool.description }}\n      {{- '\\n\\n    Args:\\n' if tool_params else '\\n' }}\n    {%- endcall %}\n    {{- '    \"\"\"\\n' }}\n  {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n\n{%- if messages[0]['role'] == 'system' %}\n  {%- set loop_messages = messages[1:] %}\n  {%- set system_message = messages[0]['content'] %}\n{%- else %}\n  {%- set loop_messages = messages %}\n  {%- set system_message = '' %}\n{%- endif %}\n{{- '<|im_start|>system\\n' + system_message if system_message or tools }}\n{%- if tools %}\n  {{- '\\n# Functions\\nHere is a list of functions that you can invoke:\\n```python\\nfrom enum import Enum\\nfrom typing import List, Dict, Optional\\nfrom pydantic import BaseModel, Field\\n\\n' }}\n  {{- tool_parser(tools) }}\n  {{- \"\\n```\\n\\n# Function Call Rule and Output Format\\n- If the user's question can be answered without calling any function, please answer the user's question directly. In this situation, you should return your thought and answer the user's question directly.\\n- If the user cannot be answered without calling any function, and the user does not provide enough information to call functions, please ask the user for more information. In this situation, you should return your thought and ask the user for more information.\\n- If the user's question cannot be answered without calling any function, and the user has provided enough information to call functions to solve it, you should call the functions. In this situation, the assistant should return your thought and call the functions.\\n- Use default parameters unless the user has specified otherwise.\\n- You should answer in the following format:\\n\\n<|thought_start|>\\n{explain why the user's question can be answered without calling a function or why you should ask the user for more information or why you should call one or more functions and your plan to solve the user's question.}\\n<|thought_end|>\\n<|tool_call_start|>\\n```python\\nfunc1(params_name=params_value, params_name2=params_value2...)\\nfunc2(params)\\n```\\n<|tool_call_end|>\\n{answer the user's question directly or ask the user for more information}\" }}\n{%- endif %}\n{{- '<|im_end|>\\n' if system_message or tools }}\n{%- for message in loop_messages %}\n  {%- set content = message.content %}\n  {%- if message.role == 'assistant' and message.tool_calls %}\n    {{- '<|im_start|>' + message.role + '\\n' }}\n    {{- '<|thought_start|>\\n' + message.thought + '\\n<|thought_end|>\\n' if message.thought }}\n    {{- '<|tool_call_start|>\\n```python\\n' }}\n    {%- for tool_call in message.tool_calls %}\n      {%- if tool_call.function is defined %}\n        {%- set tool_call = tool_call.function %}\n      {%- endif %}\n      {{- tool_call.name + '(' }}\n      {%- if tool_call.arguments is defined and tool_call.arguments|length > 0 %}\n        {%- for param_name, param_value in tool_call.arguments|items %}\n          {{- param_name + '=' + param_value|tojson }}\n          {{- ',' if not loop.last }}\n        {%- endfor %}\n      {%- endif %}\n      {{- ')\\n' }}\n    {%- endfor %}\n    {{- '```\\n<|tool_call_end|>\\n' }}\n    {{- content if content and not content.startswith('<|tool_call_start|>') }}\n    {{- '<|im_end|>\\n' }}\n  {%- elif message.role == 'assistant' and message.thought %}\n    {{- '<|im_start|>' + message.role + '\\n' + '<|thought_start|>\\n' + message.thought + '\\n<|thought_end|>\\n' + content + '<|im_end|>\\n' }}\n  {%- else %}\n    {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>\\n' }}\n  {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n  {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}