Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# ministral-3-3b-base_cp-v2.0.0-s0e2_cv-reasoning
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using /home/pinzuli/models/ministral/Ministral-3-3B-Base-2512/ as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* /home/pinzuli/swift_trainer/output/ministral-3-3b-base_cp-v2.0.0
+* /home/pinzuli/models/ministral/Ministral-3-3B-Reasoning-2512
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+# Chat Vector Merge using Task Arithmetic
+#
+# This config applies the "chat vector" from an instruct model to a target model.
+# The chat vector is computed as: chat_model - base_model
+# Then applied as: target_model + weight * (chat_model - base_model)
+#
+# Since we want to apply the chat vector to our target model (checkpoint),
+# we set the checkpoint as the base_model and only include the chat_model.
+# The task vector (chat_model - base_model) will be computed and added back.
+
+models:
+  # The instruct/chat model that provides the "chat capabilities"
+  - model: /home/pinzuli/models/ministral/Ministral-3-3B-Reasoning-2512
+    parameters:
+      weight:
+        # 1.0
+        - filter: embed_tokens
+          value: 0
+        - filter: lm_head
+          value: 0
+        - value: 1.0
+  # The target model (your fine-tuned checkpoint)
+  - model: /home/pinzuli/swift_trainer/output/ministral-3-3b-base_cp-v2.0.0
+    parameters:
+      weight: 1.0
+merge_method: task_arithmetic
+base_model: /home/pinzuli/models/ministral/Ministral-3-3B-Base-2512/
+tokenizer_source: /home/pinzuli/models/ministral/Ministral-3-3B-Reasoning-2512
+dtype: bfloat16
+
+```

chat_template.jinja

@@ -0,0 +1,135 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '# 你應該如何思考與回答
+
+首先，請先撰寫你的思考過程(內在獨白)，直到你得出回應為止。請使用 Markdown 格式化你的回應，並在任何數學方程式中使用 LaTeX。你的思考內容與最終回應必須使用與輸入相同的語言，並同時寫在同一份回應中。
+
+你的思考過程必須遵循以下範本：
+
+[THINK]
+你的想法或／以及草稿，就像在草稿紙上解題一樣。在你有信心產生對使用者的回應之前，可以隨意、輕鬆且詳細地書寫。
+[/THINK] 在此，提供給使用者的回應。' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text and thinking 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'] }}
+            {%- elif block['type'] == 'thinking' %}
+                {{- '[THINK]' + block['thinking'] + '[/THINK]' }}
+            {%- else %}
+                {{- raise_exception('Only text and thinking 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, image and thinking 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 and message['content'] != '' %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] == 'thinking' %}
+                    {{- '[THINK]' + block['thinking'] + '[/THINK]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and thinking 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'] %}
+                {{- '[TOOL_CALLS]' }}
+                {%- set name = tool['function']['name'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- name + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {{- 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 %}
+[THINK]

config.json

@@ -2,22 +2,14 @@
   "architectures": [
     "Mistral3ForConditionalGeneration"
   ],
-  "bos_token_id": 1,
   "dtype": "bfloat16",
-  "eos_token_id": 2,
-  "hidden_size": 3072,
   "image_token_index": 10,
-  "keys_to_ignore_at_inference": [
-    "past_key_values"
-  ],
   "model_type": "mistral3",
   "multimodal_projector_bias": false,
-  "pad_token_id": 11,
   "projector_hidden_act": "gelu",
   "spatial_merge_size": 2,
   "text_config": {
     "attention_dropout": 0.0,
-    "dtype": "bfloat16",
     "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 3072,
@@ -43,14 +35,12 @@
     },
     "sliding_window": null,
     "tie_word_embeddings": true,
-    "use_cache": false,
+    "use_cache": true,
     "vocab_size": 131072
   },
-  "transformers_version": "5.0.0rc2",
-  "use_cache": false,
+  "transformers_version": "5.0.0.dev0",
   "vision_config": {
     "attention_dropout": 0.0,
-    "dtype": "bfloat16",
     "head_dim": 64,
     "hidden_act": "silu",
     "hidden_size": 1024,
@@ -61,7 +51,6 @@
     "num_attention_heads": 16,
     "num_channels": 3,
     "num_hidden_layers": 24,
-    "pad_token_id": 11,
     "patch_size": 14,
     "rope_parameters": {
       "rope_theta": 10000.0,

mergekit_config.yml

@@ -0,0 +1,29 @@
+# Chat Vector Merge using Task Arithmetic
+#
+# This config applies the "chat vector" from an instruct model to a target model.
+# The chat vector is computed as: chat_model - base_model
+# Then applied as: target_model + weight * (chat_model - base_model)
+#
+# Since we want to apply the chat vector to our target model (checkpoint),
+# we set the checkpoint as the base_model and only include the chat_model.
+# The task vector (chat_model - base_model) will be computed and added back.
+
+models:
+  # The instruct/chat model that provides the "chat capabilities"
+  - model: /home/pinzuli/models/ministral/Ministral-3-3B-Reasoning-2512
+    parameters:
+      weight:
+        # 1.0
+        - filter: embed_tokens
+          value: 0
+        - filter: lm_head
+          value: 0
+        - value: 1.0
+  # The target model (your fine-tuned checkpoint)
+  - model: /home/pinzuli/swift_trainer/output/ministral-3-3b-base_cp-v2.0.0
+    parameters:
+      weight: 1.0
+merge_method: task_arithmetic
+base_model: /home/pinzuli/models/ministral/Ministral-3-3B-Base-2512/
+tokenizer_source: /home/pinzuli/models/ministral/Ministral-3-3B-Reasoning-2512
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d39a55c100c83ea35bb13f0c2a15d8fc5bc7ac66b227900f13cc43b7a9ce1a
+size 4995664928

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f2a8ad8d9f7f860b5c82c62724da96f3836ed9a9982b8cd38c34f74cd62671
+size 2702576136

model.safetensors.index.json

@@ -0,0 +1,466 @@
+{
+  "metadata": {
+    "total_size": 7698180096,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "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": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "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": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.patch_merger.merging_layer.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.ln_pre.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.patch_conv.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00002-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"
+  }
+}

processor_config.json

@@ -17,7 +17,7 @@
       0.4578275,
       0.40821073
     ],
-    "image_processor_type": "PixtralImageProcessor",
+    "image_processor_type": "PixtralImageProcessorFast",
     "image_seq_length": null,
     "image_std": [
       0.26862954,
@@ -26,10 +26,8 @@
     ],
     "input_data_format": null,
     "pad_size": null,
-    "patch_size": {
-      "height": 14,
-      "width": 14
-    },
+    "patch_size": 14,
+    "processor_class": "PixtralProcessor",
     "resample": 3,
     "rescale_factor": 0.00392156862745098,
     "return_tensors": null,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
-size 17078110
+oid sha256:11121c9e133fbe4cdd909c50f6ba00a03e3ff1c39761c518e98f4d3cce0ce99a
+size 17077881

tokenizer_config.json

@@ -1007,12 +1007,11 @@
     "<SPECIAL_999>"
   ],
   "is_local": true,
-  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "model_specific_special_tokens": {},
   "pad_token": "<pad>",
   "processor_class": "PixtralProcessor",
-  "tokenizer_class": "TokenizersBackend",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }