Add MLX 3-bit quantized weights

.gitattributes

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

chat_template.jinja

@@ -0,0 +1,122 @@
+{%- set available_tools_string, thought_instructions, add_tool_id, tool_output_format = '', '', true, "default" -%}
+
+{%- if tools is not none and tools|length > 0 -%}
+    {%- set available_tools_string -%}
+You are provided with function signatures within <available_tools></available_tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about the arguments. You should infer the argument values from previous user responses and the system message. Here are the available tools:
+<available_tools>
+{% for tool in tools %}
+{{ tool|string }}
+{% endfor %}
+</available_tools>
+{%- endset -%}
+{%- endif -%}
+{%- if tool_output_format is none or tool_output_format == "default" -%}
+{%- set tool_output_instructions -%}
+Return all function calls as a list of json objects within <tool_call></tool_call> XML tags. Each json object should contain a function name and arguments as follows:
+<tool_calls>[{"name": <function-name-1>, "arguments": <args-dict-1>}, {"name": <function-name-2>, "arguments": <args-dict-2>},...]</tool_calls>
+{%- endset -%}
+{%- elif tool_output_format == "yaml" -%}
+{%- set tool_output_instructions -%}
+Return all function calls as a list of yaml objects within <tool_call></tool_call> XML tags. Each yaml object should contain a function name and arguments as follows:
+<tool_calls>
+- name: <function-name-1>
+  arguments: <args-dict-1>
+- name: <function-name-2>
+  arguments: <args-dict-2>
+...
+</tool_calls>
+{%- endset -%}
+{%- endif -%}
+{%- if add_thoughts -%}
+{%- set thought_instructions -%}
+Prior to generating the function calls, you should generate the reasoning for why you're calling the function. Please generate these reasoning thoughts between <thinking> and </thinking> XML tags.
+{%- endset -%}
+{%- endif -%}
+{{- bos_token -}}
+{%- set reasoning_prompt='You are a thoughtful and systematic AI assistant built by ServiceNow Language Models (SLAM) lab. Before providing an answer, analyze the problem carefully and present your reasoning step by step. After explaining your thought process, provide the final solution in the following format: [BEGIN FINAL RESPONSE] ... [END FINAL RESPONSE].' -%}
+{%- if messages[0]['role'] != 'system' and tools is not none and tools|length > 0 -%}
+    {{- '<|system|>\n' + reasoning_prompt + available_tools_string + "\n" + tool_output_instructions + '\n<|end|>\n' -}}
+{%- endif -%}
+{%- if messages|selectattr('role', 'equalto', 'system')|list|length == 0 -%}
+{{- '<|system|>\n' + reasoning_prompt + '\n<|end|>\n' -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{- '<|user|>\n' }}
+        {%- if message['content'] is not string %}
+            {%- for chunk in message['content'] %}
+                {%- if chunk['type'] == 'text' %}
+                    {{- chunk['text'] }}
+                {%- elif chunk['type'] == 'image' or chunk['type'] == 'image_url'%}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Unrecognized content type!') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- else %}
+            {{- message['content'] }}
+        {%- endif %}
+        {{- '\n<|end|>\n' }}
+    {%- elif message['role'] == 'content' -%}
+        {%- if message['content'] is not string %}
+            {{- '<|content|>\n' + message['content'][0]['text'] + '\n<|end|>\n' -}}
+        {%- else %}
+            {{- '<|content|>\n' + message['content'] + '\n<|end|>\n' -}}
+        {%- endif -%}
+    {%- elif message['role'] == 'system' -%}
+        {%- if message['content'] is not none and message['content']|length > 0 %}
+            {%- if message['content'] is string %}
+                {%- set system_message = message['content'] %}
+            {%- else %}
+                {%- set system_message = message['content'][0]['text'] %}
+            {%- endif %}
+        {%- else %}
+            {%- set system_message = '' %}
+        {%- endif %}
+        {%- if tools is not none and tools|length > 0 -%}
+            {{- '<|system|>\n' + reasoning_prompt + system_message + '\n' + available_tools_string + '\n<|end|>\n' -}}
+        {%- else -%}
+            {{- '<|system|>\n' + reasoning_prompt + system_message + '\n<|end|>\n' -}}
+        {%- endif -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- if loop.last -%}
+            {%- set add_tool_id = false -%}
+        {%- endif -%}
+        {{- '<|assistant|>\n' -}}
+        {%- if message['content'] is not none and message['content']|length > 0 -%}
+            {%- if message['content'] is not string and message['content'][0]['text'] is not none %}
+                {{- message['content'][0]['text'] }}
+            {%- else %}
+                {{- message['content'] -}}
+            {%- endif -%}
+        {%- elif message['chosen'] is not none and message['chosen']|length > 0 -%}
+            {{- message['chosen'][0] -}}
+        {%- endif -%}
+        {%- if add_thoughts and 'thought' in message and message['thought'] is not none -%}
+            {{- '<thinking>' + message['thought'] + '</thinking>' -}}
+        {%- endif -%}
+        {%- if message['tool_calls'] is not none and message['tool_calls']|length > 0 -%}
+            {{- '\n<tool_calls>[' -}}
+            {%- for tool_call in message["tool_calls"] -%}
+                {{- '{"name": "' + tool_call['function']['name'] + '", "arguments": ' + tool_call['function']['arguments']|string -}}
+                {%- if add_tool_id == true -%}
+                    {{- ', "id": "' + tool_call['id'] + '"' -}}
+                {%- endif -%}
+                {{- '}' -}}
+                {%- if not loop.last -%}{{- ', ' -}}{%- endif -%}
+            {%- endfor -%}
+            {{- ']</tool_calls>' -}}
+        {%- endif -%}
+        {{- '\n<|end|>\n' + eos_token -}}
+    {%- elif message['role'] == 'tool' -%}
+        {%- if message['content'] is string %}
+            {%- set tool_message = message['content'] %}
+        {%- else %}
+            {%- set tool_message = message['content'][0]['text'] %}
+        {%- endif -%}
+        {{- '<|tool_result|>\n' + tool_message|string + '\n<|end|>\n' -}}
+    {%- endif -%}
+    {%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
+        {{- '<|assistant|>\n' -}}
+    {%- endif -%}
+{%- endfor -%}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- set available_tools_string, thought_instructions, add_tool_id, tool_output_format = '', '', true, \"default\" -%}\n\n{%- if tools is not none and tools|length > 0 -%}\n    {%- set available_tools_string -%}\nYou are provided with function signatures within <available_tools></available_tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about the arguments. You should infer the argument values from previous user responses and the system message. Here are the available tools:\n<available_tools>\n{% for tool in tools %}\n{{ tool|string }}\n{% endfor %}\n</available_tools>\n{%- endset -%}\n{%- endif -%}\n{%- if tool_output_format is none or tool_output_format == \"default\" -%}\n{%- set tool_output_instructions -%}\nReturn all function calls as a list of json objects within <tool_call></tool_call> XML tags. Each json object should contain a function name and arguments as follows:\n<tool_calls>[{\"name\": <function-name-1>, \"arguments\": <args-dict-1>}, {\"name\": <function-name-2>, \"arguments\": <args-dict-2>},...]</tool_calls>\n{%- endset -%}\n{%- elif tool_output_format == \"yaml\" -%}\n{%- set tool_output_instructions -%}\nReturn all function calls as a list of yaml objects within <tool_call></tool_call> XML tags. Each yaml object should contain a function name and arguments as follows:\n<tool_calls>\n- name: <function-name-1>\n  arguments: <args-dict-1>\n- name: <function-name-2>\n  arguments: <args-dict-2>\n...\n</tool_calls>\n{%- endset -%}\n{%- endif -%}\n{%- if add_thoughts -%}\n{%- set thought_instructions -%}\nPrior to generating the function calls, you should generate the reasoning for why you're calling the function. Please generate these reasoning thoughts between <thinking> and </thinking> XML tags.\n{%- endset -%}\n{%- endif -%}\n{{- bos_token -}}\n{%- set reasoning_prompt='You are a thoughtful and systematic AI assistant built by ServiceNow Language Models (SLAM) lab. Before providing an answer, analyze the problem carefully and present your reasoning step by step. After explaining your thought process, provide the final solution in the following format: [BEGIN FINAL RESPONSE] ... [END FINAL RESPONSE].' -%}\n{%- if messages[0]['role'] != 'system' and tools is not none and tools|length > 0 -%}\n    {{- '<|system|>\\n' + reasoning_prompt + available_tools_string + \"\\n\" + tool_output_instructions + '\\n<|end|>\\n' -}}\n{%- endif -%}\n{%- if messages|selectattr('role', 'equalto', 'system')|list|length == 0 -%}\n{{- '<|system|>\\n' + reasoning_prompt + '\\n<|end|>\\n' -}}\n{%- endif -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'user' -%}\n        {{- '<|user|>\\n' }}\n        {%- if message['content'] is not string %}\n            {%- for chunk in message['content'] %}\n                {%- if chunk['type'] == 'text' %}\n                    {{- chunk['text'] }}\n                {%- elif chunk['type'] == 'image' or chunk['type'] == 'image_url'%}\n                    {{- '[IMG]' }}\n                {%- else %}\n                    {{- raise_exception('Unrecognized content type!') }}\n                {%- endif %}\n            {%- endfor %}\n        {%- else %}\n            {{- message['content'] }}\n        {%- endif %}\n        {{- '\\n<|end|>\\n' }}\n    {%- elif message['role'] == 'content' -%}\n        {%- if message['content'] is not string %}\n            {{- '<|content|>\\n' + message['content'][0]['text'] + '\\n<|end|>\\n' -}}\n        {%- else %}\n            {{- '<|content|>\\n' + message['content'] + '\\n<|end|>\\n' -}}\n        {%- endif -%}\n    {%- elif message['role'] == 'system' -%}\n        {%- if message['content'] is not none and message['content']|length > 0 %}\n            {%- if message['content'] is string %}\n                {%- set system_message = message['content'] %}\n            {%- else %}\n                {%- set system_message = message['content'][0]['text'] %}\n            {%- endif %}\n        {%- else %}\n            {%- set system_message = '' %}\n        {%- endif %}\n        {%- if tools is not none and tools|length > 0 -%}\n            {{- '<|system|>\\n' + reasoning_prompt + system_message + '\\n' + available_tools_string + '\\n<|end|>\\n' -}}\n        {%- else -%}\n            {{- '<|system|>\\n' + reasoning_prompt + system_message + '\\n<|end|>\\n' -}}\n        {%- endif -%}\n    {%- elif message['role'] == 'assistant' -%}\n        {%- if loop.last -%}\n            {%- set add_tool_id = false -%}\n        {%- endif -%}\n        {{- '<|assistant|>\\n' -}}\n        {%- if message['content'] is not none and message['content']|length > 0 -%}\n            {%- if message['content'] is not string and message['content'][0]['text'] is not none %}\n                {{- message['content'][0]['text'] }}\n            {%- else %}\n                {{- message['content'] -}}\n            {%- endif -%}\n        {%- elif message['chosen'] is not none and message['chosen']|length > 0 -%}\n            {{- message['chosen'][0] -}}\n        {%- endif -%}\n        {%- if add_thoughts and 'thought' in message and message['thought'] is not none -%}\n            {{- '<thinking>' + message['thought'] + '</thinking>' -}}\n        {%- endif -%}\n        {%- if message['tool_calls'] is not none and message['tool_calls']|length > 0 -%}\n            {{- '\\n<tool_calls>[' -}}\n            {%- for tool_call in message[\"tool_calls\"] -%}\n                {{- '{\"name\": \"' + tool_call['function']['name'] + '\", \"arguments\": ' + tool_call['function']['arguments']|string -}}\n                {%- if add_tool_id == true -%}\n                    {{- ', \"id\": \"' + tool_call['id'] + '\"' -}}\n                {%- endif -%}\n                {{- '}' -}}\n                {%- if not loop.last -%}{{- ', ' -}}{%- endif -%}\n            {%- endfor -%}\n            {{- ']</tool_calls>' -}}\n        {%- endif -%}\n        {{- '\\n<|end|>\\n' + eos_token -}}\n    {%- elif message['role'] == 'tool' -%}\n        {%- if message['content'] is string %}\n            {%- set tool_message = message['content'] %}\n        {%- else %}\n            {%- set tool_message = message['content'][0]['text'] %}\n        {%- endif -%}\n        {{- '<|tool_result|>\\n' + tool_message|string + '\\n<|end|>\\n' -}}\n    {%- endif -%}\n    {%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}\n        {{- '<|assistant|>\\n' -}}\n    {%- endif -%}\n{%- endfor -%}"
+}

config.json

@@ -0,0 +1,237 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "LlavaForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": "bfloat16",
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "ignore_index": -100,
+    "image_seq_length": 1,
+    "image_token_index": 10,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "llava",
+    "multimodal_projector_bias": true,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "projector_hidden_act": "gelu",
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 3,
+        "mode": "affine"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_config": {
+        "vocab_size": 131072,
+        "max_position_embeddings": 262400,
+        "hidden_size": 5120,
+        "intermediate_size": 14336,
+        "num_hidden_layers": 48,
+        "num_attention_heads": 32,
+        "sliding_window": null,
+        "head_dim": 128,
+        "num_key_value_heads": 8,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-05,
+        "use_cache": true,
+        "rope_theta": 1000000000.0,
+        "attention_dropout": 0.0,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": null,
+        "pruned_heads": {},
+        "tie_word_embeddings": false,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 1,
+        "pad_token_id": null,
+        "eos_token_id": 2,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
+        "model_type": "mistral",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "output_attentions": false
+    },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.56.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": null,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
+        "head_dim": 64,
+        "model_type": "pixtral",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "hidden_size": 1024,
+        "intermediate_size": 4096,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 16,
+        "image_size": 1024,
+        "attention_dropout": 0.0,
+        "hidden_act": "silu",
+        "rope_theta": 10000.0,
+        "initializer_range": 0.02,
+        "output_attentions": false
+    },
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "full"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4857bed80098f1eec5d09c330903e88ae3a51bdea29e86015947876910417ac4
+size 5363242955

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2ff2d7ed0c3f77a4ce4baa0557428a7b120060c48386190fd714d0bf3754cf
+size 1771117265

model.safetensors.index.json

@@ -0,0 +1,664 @@
+{
+  "metadata": {
+    "total_size": 29727719424
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.norm.weight": "model-00006-of-00007.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00007.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00007.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00007.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.ln_pre.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.patch_conv.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
+    "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00007.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

processor_config.json

@@ -0,0 +1,8 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 16,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 1
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f33e6f52b2833e8cc17229af8eea363f640a898f19a48184a2c7f6f5a88337
+size 17077329