Upload folder using huggingface_hub

.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

README.md

@@ -0,0 +1,9 @@
+---
+library_name: mlx
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
+pipeline_tag: text-generation
+tags:
+- mlx
+base_model: Qwen/Qwen3-4B-Instruct-2507
+---

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,1192 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.embed_tokens": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.1.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.2.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.3.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.embed_tokens": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.0.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.1.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.2.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.2.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.3.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.3.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.4.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.5.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.6.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.7.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.8.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.9.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.10.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.11.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.12.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.13.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.14.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.15.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.16.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.17.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.18.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.19.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.20.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.21.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.22.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.23.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.self_attn.o_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.24.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.25.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.26.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.27.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.28.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.29.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.30.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.31.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.32.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.33.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.q_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.34.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.self_attn.k_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.self_attn.v_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.gate_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.down_proj": {
+            "bits": 5,
+            "group_size": 64
+        },
+        "model.layers.35.mlp.up_proj": {
+            "bits": 5,
+            "group_size": 64
+        }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 5000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "pad_token_id": 151643,
+    "temperature": 0.7,
+    "top_k": 20,
+    "top_p": 0.8,
+    "transformers_version": "4.51.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe23defac0f07d6f7c35d21fa2229027e6db329bad5322c33d45c4a8b11188c
+size 2516442069

model.safetensors.index.json

@@ -0,0 +1,912 @@
+{
+    "metadata": {
+        "total_size": 2516339712,
+        "total_parameters": 4022468096
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.24.input_layernorm.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.25.input_layernorm.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.26.input_layernorm.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.27.input_layernorm.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.28.input_layernorm.weight": "model.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.29.input_layernorm.weight": "model.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.30.input_layernorm.weight": "model.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.31.input_layernorm.weight": "model.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.32.input_layernorm.weight": "model.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.32.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.33.input_layernorm.weight": "model.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.33.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.34.input_layernorm.weight": "model.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.34.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.35.input_layernorm.weight": "model.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.35.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d47c87966b4db779200053de490f89936ed529f8ab889244e271630715fcfe
+size 11422638

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}