Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,40 @@
+---
+library_name: mlx
+inference: false
+base_model: mistralai/Devstral-Small-2-24B-Instruct-2512
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+tags:
+- mistral-common
+- mlx
+license: apache-2.0
+pipeline_tag: text-generation
+---
+
+# jritchie-nullable/Devstral-Small-2-24B-Instruct-2512-MLX-8bit
+
+This model [jritchie-nullable/Devstral-Small-2-24B-Instruct-2512-MLX-8bit](https://huggingface.co/jritchie-nullable/Devstral-Small-2-24B-Instruct-2512-MLX-8bit) was
+converted to MLX format from [mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512)
+using mlx-lm version **0.28.4**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("jritchie-nullable/Devstral-Small-2-24B-Instruct-2512-MLX-8bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+    {{- '[SYSTEM_PROMPT]' -}}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] -}}
+    {%- else %}        
+        {%- for block in messages[0]['content'] %}
+            {%- if block['type'] == 'text' %}
+                {{- block['text'] }}
+            {%- else %}
+                {{- raise_exception('Only text chunks are supported in system message contents.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '[/SYSTEM_PROMPT]' -}}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- if default_system_message != '' %}
+        {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+    {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+        {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+            {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+    {#- User messages supports text content or text and image chunks. #}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text content or text and image chunks. #}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+            {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+        {%- endif %}
+
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {#- End of sequence token for each assistant messages. #}
+        {{- eos_token }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role'] + '.') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,54 @@
+{
+    "architectures": [
+        "Mistral3ForConditionalGeneration"
+    ],
+    "dtype": "bfloat16",
+    "image_token_index": 10,
+    "model_type": "mistral3",
+    "multimodal_projector_bias": false,
+    "projector_hidden_act": "gelu",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "spatial_merge_size": 2,
+    "text_config": {
+        "attention_dropout": 0.0,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "intermediate_size": 32768,
+        "max_position_embeddings": 393216,
+        "model_type": "ministral3",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 40,
+        "num_key_value_heads": 8,
+        "rms_norm_eps": 1e-05,
+        "rope_parameters": {
+            "beta_fast": 32.0,
+            "beta_slow": 1.0,
+            "factor": 48.0,
+            "llama_4_scaling_beta": 0.1,
+            "mscale": 1.0,
+            "mscale_all_dim": 1.0,
+            "original_max_position_embeddings": 8192,
+            "rope_theta": 100000000.0,
+            "rope_type": "yarn",
+            "type": "yarn"
+        },
+        "sliding_window": null,
+        "use_cache": true,
+        "vocab_size": 131072,
+        "tie_word_embeddings": false
+    },
+    "tie_word_embeddings": false,
+    "transformers_version": "5.0.0.dev0",
+    "vision_feature_layer": -1
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392a7347f0aff69b78804e7680074157d50ae2d692251e5b058df61d5de61b68
+size 5258775412

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfadcffc13781735235947d2ba860103a54afe5209ad84bda4e6c5d2dbb86fe7
+size 5314525437

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6147912cbd3272d9067fa939eac708fbf9bb0d2484a79434ce94fd78a913be
+size 5314525492

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9343defb00c111cd58e1c705827a722310e8d8419e27423363d62d0fdd0e760
+size 5314525460

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadeb0233011a488368d7050ffd26b18a4f629f98459b611d23bf66616df134b
+size 3843835544

model.safetensors.index.json

@@ -0,0 +1,935 @@
+{
+    "metadata": {
+        "total_size": 25046067200,
+        "total_parameters": 23572403200
+    },
+    "weight_map": {
+        "language_model.lm_head.biases": "model-00005-of-00005.safetensors",
+        "language_model.lm_head.scales": "model-00005-of-00005.safetensors",
+        "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.embed_tokens.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.embed_tokens.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.down_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.down_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.o_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.o_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.o_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.o_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.o_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.o_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.o_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.o_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.o_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.o_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.down_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.down_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.up_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.up_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.o_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.o_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "language_model.model.norm.weight": "model-00005-of-00005.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286acad9b0e27fce778ac429763536accf618ccb6ed72963b6f94685e531c5c7
+size 17077402

tokenizer_config.json

@@ -0,0 +1,1014 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "[AUDIO]",
+    "[BEGIN_AUDIO]",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "[ARGS]",
+    "[CALL_ID]",
+    "[THINK]",
+    "[/THINK]",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "PixtralProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}