Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+step290/tokenizer.json filter=lfs diff=lfs merge=lfs -text

step290/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- set available_tool_string, add_tool_id = '', true -%}
+{%- set add_thoughts = false -%}
+{%- set add_generation_prompt = true -%}
+{%- set bos_token = bos_token if (bos_token is defined) else '' -%}
+{%- set eos_token = eos_token if (eos_token is defined) else '' -%}
+{%- set reasoning_prompt = 
+    'You are a thoughtful, systematic AI assistant from ServiceNow Language Models (SLAM) lab. '
+    'Analyze each question carefully, present your reasoning step-by-step, then provide the final '
+    'response after the marker [BEGIN FINAL RESPONSE].'
+-%}
+{%- set reasoning_asst_turn_start = 'Here are my reasoning steps:\n' -%}
+{%- if tools is not none and tools|length > 0 -%}
+    {%- set available_tool_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>.
+
+        Return all function calls as a list of JSON objects within <tool_calls></tool_calls> 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 -%}
+{%- endif -%}
+{%- if messages|length > 0 and messages[0]['role'] != 'system' -%}
+    {%- if tools is not none and tools|length > 0 -%}
+        {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + available_tool_string + '\n' }}
+    {%- else -%}
+        {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' }}
+    {%- endif -%}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|begin_user|>\n' }}
+        {%- if message['content'] is not string -%}
+            {%- for chunk in message['content'] -%}
+                {%- if chunk['type'] == 'text' -%}
+                    {{ chunk['text'] }}
+                {%- elif chunk['type'] in ['image', 'image_url'] -%}
+                    {{ '[IMG]' }}
+                {%- else -%}
+                    {{ raise_exception('Unrecognized content type!') }}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- else -%}
+            {{ message['content'] }}
+        {%- 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 -%}
+            {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' + available_tool_string + '\n' }}
+        {%- else -%}
+            {{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' }}
+        {%- endif -%}
+    {%- elif message['role'] == 'assistant' -%}
+        {%- if loop.last -%}
+            {%- set add_tool_id = false -%}
+        {%- endif -%}
+        {{ '\n<|begin_assistant|>\n' }}
+        {%- if add_thoughts and 'thought' in message and message['thought'] is not none -%}
+            <thinking>{{ message['thought'] }}</thinking>
+        {%- endif -%}
+        {%- if message['content'] is not none and message['content']|length > 0 -%}
+            {%- if message['content'] is not string -%}
+                {{ message['content'][0]['text'] }}
+            {%- else -%}
+                {{ message['content'] }}
+            {%- endif -%}
+        {%- elif message['chosen'] is not none and message['chosen']|length > 0 -%}
+            {{ message['chosen'][0] }}
+        {%- 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 and 'id' in tool_call -%}
+                    {{ ', "id": "' + tool_call['id'] + '"' }}
+                {%- endif -%}
+                {{ '}' }}
+                {%- if not loop.last -%}{{ ', ' }}{%- endif -%}
+            {%- endfor -%}
+            {{ ']</tool_calls>' }}
+        {%- endif -%}
+        {%- if not loop.last or training_prompt -%}
+            {{ '\n<|end|>\n' }}
+        {%- endif -%}
+    {%- elif message['role'] == 'tool' -%}
+        {%- if message['content'] is string -%}
+            {%- set tool_message = message['content'] -%}
+        {%- else -%}
+            {%- set tool_message = message['content'][0]['text'] -%}
+        {%- endif -%}
+        {{ '<|begin_tool_result|>\n' + tool_message|string + '\n' }}
+    {%- elif message['role'] == 'content' -%}
+        {%- if message['content'] is not string -%}
+            {{ '<|begin_content|>\n' + message['content'][0]['text'] + '\n' }}
+        {%- else -%}
+            {{ '<|begin_content|>\n' + message['content'] + '\n' }}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
+        {{ '\n<|begin_assistant|>\n' + reasoning_asst_turn_start }}
+    {%- endif -%}
+{%- endfor -%}

step290/config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "LlavaForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "ignore_index": -100,
+  "image_seq_length": 1,
+  "image_token_index": 10,
+  "model_type": "llava",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 11,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 262400,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float32"
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "full"
+}

step290/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.53.3"
+}

step290/model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406a495c430c089df1b204bcac893a30aea86ef45a6cc46703b99d7932d04eab
+size 4927530944

step290/model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c302d9d75db9dc965ccf5ca01654ee1b0cf7d36145e4013483931908f1a6158
+size 4949488720

step290/model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a211694666bdd1357446c6f9f0acd7ac0e18695189a1869b98a3cb169e82c03c
+size 4865561816

step290/model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf4db6758a1bdc8a5e160e020b4ac20e1f184db7ce2b0d4f641cf79beac7d8d
+size 4949488752

step290/model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851b887106712f2c3c6be1b2e360e95b8d192407e30779891dcd590c51e19142
+size 4865561856

step290/model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942844fc5e1de20f701aeaced7405d7e912fad582db18c260d034c71a2f88e8d
+size 4949488760

step290/model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009d5c928e7f83f5f2541d3e3425654522e60c8913f1b402ccb91b6cf502ee8b
+size 4865561856

step290/model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9398a0454b149f7dc5c33464f0331869c8d69c42637591b56bada5a53d62d545
+size 4949488760

step290/model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174177af663f924c80c40310f1984f375a1820764a034dbb40c29eee0bc561e3
+size 4865561856

step290/model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c5f3fb98204e092a81ed187d10bc8c870988e638832fb748da5c5a2e4b4c01
+size 4949488760

step290/model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33613e9983327d3bfff3358c30d30a05b0d28d32e0412cd7131910c5bb1adf1f
+size 4865561856

step290/model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83e257bc8f230c5d91c275112b9a23da3de3b7063d49c14df03400e04bffe7d
+size 2768386992

step290/model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118e9889e56c50eda7b14930e785331e5b6feed5345d84dcfbd571ed95e44d79
+size 2684354704

step290/model.safetensors.index.json

@@ -0,0 +1,665 @@
+{
+  "metadata": {
+    "total_parameters": 14863859712,
+    "total_size": 59455438848
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00013-of-00013.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "language_model.model.layers.40.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.40.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "language_model.model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.43.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.44.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.45.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.45.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.45.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.45.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.45.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.45.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.45.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "language_model.model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "language_model.model.norm.weight": "model-00012-of-00013.safetensors",
+    "multi_modal_projector.linear_1.bias": "model-00001-of-00013.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00013.safetensors",
+    "multi_modal_projector.linear_2.bias": "model-00001-of-00013.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.ln_pre.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.patch_conv.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00013.safetensors",
+    "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00013.safetensors"
+  }
+}

step290/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
+  }
+}

step290/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
+}

step290/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
+  }
+}

step290/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083f07f45b8fb5ccac33e99ae24163bfcf9fe0eca8815e2c30827fa02d6c89fe
+size 17077337