Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+tekken.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

SYSTEM_PROMPT.txt

@@ -0,0 +1,29 @@
+You are Ministral-3-3B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
+You power an AI assistant called Le Chat.
+Your knowledge base was last updated on 2023-10-01.
+The current date is {today}.
+
+When you're not sure about some information or when the user's request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don't have the information and avoid making up anything.
+If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").
+You are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.
+You follow these instructions in all languages, and always respond to the user in the language they use or request.
+Next sections describe the capabilities that you have.
+
+# WEB BROWSING INSTRUCTIONS
+
+You cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.
+
+# MULTI-MODAL INSTRUCTIONS
+
+You have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.
+You cannot read nor transcribe audio files or videos.
+
+# TOOL CALLING INSTRUCTIONS
+
+You may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:
+
+1. When the request requires up-to-date information.
+2. When the request requires specific data that you do not have in your knowledge base.
+3. When the request involves actions that you cannot perform without tools.
+
+Always prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = 'You are Ministral-3-3B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYou power an AI assistant called Le Chat.\nYour knowledge base was last updated on 2023-10-01.\nThe current date is {today}.\n\nWhen you\'re not sure about some information or when the user\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\'t have the information and avoid making up anything.\nIf the user\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\nNext sections describe the capabilities that you have.\n\n# WEB BROWSING INSTRUCTIONS\n\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\n\n# MULTI-MODAL INSTRUCTIONS\n\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\nYou cannot read nor transcribe audio files or videos.\n\n# TOOL CALLING INSTRUCTIONS\n\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\n\n1. When the request requires up-to-date information.\n2. When the request requires specific data that you do not have in your knowledge base.\n3. When the request involves actions that you cannot perform without tools.\n\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}
+
+{#- 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 +1,267 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 8,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.vision_tower.transformer.layers.0.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.0.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.0.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.0.attention.k_proj",
+      "model.vision_tower.transformer.layers.0.attention.v_proj",
+      "model.vision_tower.transformer.layers.0.attention.q_proj",
+      "model.vision_tower.transformer.layers.0.attention.o_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.1.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.1.attention.k_proj",
+      "model.vision_tower.transformer.layers.1.attention.v_proj",
+      "model.vision_tower.transformer.layers.1.attention.q_proj",
+      "model.vision_tower.transformer.layers.1.attention.o_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.2.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.2.attention.k_proj",
+      "model.vision_tower.transformer.layers.2.attention.v_proj",
+      "model.vision_tower.transformer.layers.2.attention.q_proj",
+      "model.vision_tower.transformer.layers.2.attention.o_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.3.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.3.attention.k_proj",
+      "model.vision_tower.transformer.layers.3.attention.v_proj",
+      "model.vision_tower.transformer.layers.3.attention.q_proj",
+      "model.vision_tower.transformer.layers.3.attention.o_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.4.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.4.attention.k_proj",
+      "model.vision_tower.transformer.layers.4.attention.v_proj",
+      "model.vision_tower.transformer.layers.4.attention.q_proj",
+      "model.vision_tower.transformer.layers.4.attention.o_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.5.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.5.attention.k_proj",
+      "model.vision_tower.transformer.layers.5.attention.v_proj",
+      "model.vision_tower.transformer.layers.5.attention.q_proj",
+      "model.vision_tower.transformer.layers.5.attention.o_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.6.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.6.attention.k_proj",
+      "model.vision_tower.transformer.layers.6.attention.v_proj",
+      "model.vision_tower.transformer.layers.6.attention.q_proj",
+      "model.vision_tower.transformer.layers.6.attention.o_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.7.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.7.attention.k_proj",
+      "model.vision_tower.transformer.layers.7.attention.v_proj",
+      "model.vision_tower.transformer.layers.7.attention.q_proj",
+      "model.vision_tower.transformer.layers.7.attention.o_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.8.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.8.attention.k_proj",
+      "model.vision_tower.transformer.layers.8.attention.v_proj",
+      "model.vision_tower.transformer.layers.8.attention.q_proj",
+      "model.vision_tower.transformer.layers.8.attention.o_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.9.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.9.attention.k_proj",
+      "model.vision_tower.transformer.layers.9.attention.v_proj",
+      "model.vision_tower.transformer.layers.9.attention.q_proj",
+      "model.vision_tower.transformer.layers.9.attention.o_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.10.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.10.attention.k_proj",
+      "model.vision_tower.transformer.layers.10.attention.v_proj",
+      "model.vision_tower.transformer.layers.10.attention.q_proj",
+      "model.vision_tower.transformer.layers.10.attention.o_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.11.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.11.attention.k_proj",
+      "model.vision_tower.transformer.layers.11.attention.v_proj",
+      "model.vision_tower.transformer.layers.11.attention.q_proj",
+      "model.vision_tower.transformer.layers.11.attention.o_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.12.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.12.attention.k_proj",
+      "model.vision_tower.transformer.layers.12.attention.v_proj",
+      "model.vision_tower.transformer.layers.12.attention.q_proj",
+      "model.vision_tower.transformer.layers.12.attention.o_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.13.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.13.attention.k_proj",
+      "model.vision_tower.transformer.layers.13.attention.v_proj",
+      "model.vision_tower.transformer.layers.13.attention.q_proj",
+      "model.vision_tower.transformer.layers.13.attention.o_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.14.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.14.attention.k_proj",
+      "model.vision_tower.transformer.layers.14.attention.v_proj",
+      "model.vision_tower.transformer.layers.14.attention.q_proj",
+      "model.vision_tower.transformer.layers.14.attention.o_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.15.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.15.attention.k_proj",
+      "model.vision_tower.transformer.layers.15.attention.v_proj",
+      "model.vision_tower.transformer.layers.15.attention.q_proj",
+      "model.vision_tower.transformer.layers.15.attention.o_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.16.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.16.attention.k_proj",
+      "model.vision_tower.transformer.layers.16.attention.v_proj",
+      "model.vision_tower.transformer.layers.16.attention.q_proj",
+      "model.vision_tower.transformer.layers.16.attention.o_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.17.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.17.attention.k_proj",
+      "model.vision_tower.transformer.layers.17.attention.v_proj",
+      "model.vision_tower.transformer.layers.17.attention.q_proj",
+      "model.vision_tower.transformer.layers.17.attention.o_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.18.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.18.attention.k_proj",
+      "model.vision_tower.transformer.layers.18.attention.v_proj",
+      "model.vision_tower.transformer.layers.18.attention.q_proj",
+      "model.vision_tower.transformer.layers.18.attention.o_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.19.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.19.attention.k_proj",
+      "model.vision_tower.transformer.layers.19.attention.v_proj",
+      "model.vision_tower.transformer.layers.19.attention.q_proj",
+      "model.vision_tower.transformer.layers.19.attention.o_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.20.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.20.attention.k_proj",
+      "model.vision_tower.transformer.layers.20.attention.v_proj",
+      "model.vision_tower.transformer.layers.20.attention.q_proj",
+      "model.vision_tower.transformer.layers.20.attention.o_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.21.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.21.attention.k_proj",
+      "model.vision_tower.transformer.layers.21.attention.v_proj",
+      "model.vision_tower.transformer.layers.21.attention.q_proj",
+      "model.vision_tower.transformer.layers.21.attention.o_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.22.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.22.attention.k_proj",
+      "model.vision_tower.transformer.layers.22.attention.v_proj",
+      "model.vision_tower.transformer.layers.22.attention.q_proj",
+      "model.vision_tower.transformer.layers.22.attention.o_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.gate_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.up_proj",
+      "model.vision_tower.transformer.layers.23.feed_forward.down_proj",
+      "model.vision_tower.transformer.layers.23.attention.k_proj",
+      "model.vision_tower.transformer.layers.23.attention.v_proj",
+      "model.vision_tower.transformer.layers.23.attention.q_proj",
+      "model.vision_tower.transformer.layers.23.attention.o_proj",
+      "model.multi_modal_projector.patch_merger.merging_layer",
+      "model.multi_modal_projector.linear_1",
+      "model.multi_modal_projector.linear_2",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.12.3.a20251114"
+  },
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 16.0,
+      "llama_4_scaling_beta": 0.1,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 16384,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "vision_feature_layer": -1
+}

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28921cdfeab0215dbbf7c212e14671172cfd7795fd0979b07f38f044ed89c0ed
+size 5666529360

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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffddfa18d75a56ce290db7d6ee37cd5e247d250c94d1e5bf9cc92b492f23798
+size 4999543008

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44af8ed7eed63d50f9c00d05148d035468b60bb5485058b02a0892c0cbb679ab
+size 667000128

model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_parameters": 2076669292,
+    "total_size": 5666435936
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.norm.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.patch_merger.merging_layer.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_conv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

params.json

@@ -0,0 +1,47 @@
+{
+  "dim": 3072,
+  "n_layers": 26,
+  "head_dim": 128,
+  "hidden_dim": 9216,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072,
+  "tied_embeddings": true,
+  "max_position_embeddings": 262144,
+  "llama_4_scaling": {
+    "original_max_position_embeddings": 16384,
+    "beta": 0.1
+  },
+  "q_lora_rank": null,
+  "qk_rope_head_dim": null,
+  "qk_nope_head_dim": null,
+  "kv_lora_rank": null,
+  "v_head_dim": null,
+  "yarn": {
+    "original_max_position_embeddings": 16384,
+    "factor": 16,
+    "apply_scale": false,
+    "beta": 32,
+    "alpha": 1
+  },
+  "vision_encoder": {
+    "image_token_id": 10,
+    "intermediate_size": 4096,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 16,
+    "mm_projector_id": "patch_merge",
+    "spatial_merge_size": 2,
+    "hidden_size": 1024,
+    "num_channels": 3,
+    "image_size": 1540,
+    "max_image_size": 1540,
+    "patch_size": 14,
+    "rope_theta": 10000.0,
+    "add_pre_mm_projector_layer_norm": true,
+    "adapter_bias": false,
+    "image_break_token_id": 12,
+    "image_end_token_id": 13
+  }
+}

processor_config.json

@@ -0,0 +1,42 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "device": null,
+    "disable_grouping": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "PixtralImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "PixtralProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 1540
+    }
+  },
+  "image_token": "[IMG]",
+  "patch_size": 14,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 2
+}

recipe.yaml

@@ -0,0 +1,37 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 8
+            type: int
+            symmetric: true
+            group_size: 32
+            strategy: group
+            block_structure: null
+            dynamic: false
+            actorder: null
+            scale_dtype: null
+            zp_dtype: null
+            observer: mse
+            observer_kwargs: {}
+          input_activations: null
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: ['re:.*embed_tokens', 're:.*input_layernorm', 're:.*post_attention_layernorm',
+        're:.*norm', 're:.*lm_head', 're:.*multi_modal_projector.*', 're:.*vision_tower.*']
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
+      - smooth_layer: re:.*v_proj$
+        balance_layers: ['re:.*o_proj$']
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+      offload_device: !!python/object/apply:torch.device [cpu]
+      duo_scaling: true
+      n_grid: 20

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29d19ea32eb7e26e6c0572d57cb7f9eca0f4420e0e0fe6ae1cf3be94da1c0d6
+size 16753777

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
+size 17078110