Upload merged full fine-tuned checkpoint (BoundingDocs LoRA)

.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 +1,138 @@
+{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'system' -%}
+        {{- '<|im_start|>system
+' -}}
+        {%- if message['content'] is string -%}
+            {{- message['content'] | trim -}}
+        {%- endif -%}
+        {{- '<|im_end|>
+' -}}
+    {%- elif message['role'] == 'user' -%}
+        {%- if loop.first -%}
+            {{- '<|im_start|>system
+' -}}
+            {%- if template -%}
+                {#--- If template, extraction task ---#}
+                {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}
+            {%- else -%}
+                {#--- Else, template generation task ---#}
+                {{- 'You are a helpful assistant.' -}}
+            {%- endif -%}
+            {{ '<|im_end|>
+' }}
+        {%- endif -%}
+        {{- '<|im_start|>' + message['role'] + '
+' -}}
+        {%- if template -%}
+            {#--- Template Section ---#}
+            {{- '# Template:
+' -}}
+            {{- template -}}
+            {{- '
+' -}}
+
+            {%- if examples -%}
+                {#--- Examples can only exist in the extraction task ---#}
+                {{- '# Examples:
+' -}}
+                {%- for example in examples -%}
+                    {{- '## Input:
+' -}}
+                    {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}
+                        {{- image_placeholder | trim -}}
+                    {%- elif example['input'] == '<image>' -%}
+                        {#--- Keep compatibility with <image> for now ---#}
+                        {{- image_placeholder | trim -}}
+                    {%- else -%}
+                        {#--- Text input example ---#}
+                        {{- example['input'] -}}
+                    {%- endif -%}
+                    {{- '
+' -}}
+                    {{- '## Output:
+' -}}
+                    {{- example['output'] -}}
+                    {{- '
+' -}}
+                {%- endfor -%}
+            {%- endif -%}
+            {{- '# Context:
+' -}}
+        {%- endif -%}
+
+        {%- if message['content'] is string -%}
+            {#--- Simple string content ---#}
+            {{- message['content'] | trim -}}
+        {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}
+            {{- image_placeholder | trim -}}
+        {%- else -%}
+            {#--- List of content items (mixed text/images) ---#}
+            {#--- First, determine what the actual input content is (not ICL images) ---#}
+            {%- set ns = namespace(has_text_input=false, text_content='') -%}
+
+            {#--- Count content types and identify actual input document ---#}
+            {%- for content in message['content'] -%}
+                {%- if content is mapping and content.get('type') == 'text' -%}
+                    {%- if content.get('text') != '<image>' -%}
+                        {#--- Keep compatibility with <image> for now ---#}
+                        {%- set ns.has_text_input = true -%}
+                        {%- set ns.text_content = content['text'] -%}
+                    {%- endif -%}
+                {%- elif content is string -%}
+                    {%- if content != '<image>' -%}
+                        {#--- Keep compatibility with <image> for now ---#}
+                        {%- set ns.has_text_input = true -%}
+                        {%- set ns.text_content = content -%}
+                    {%- endif -%}
+                {%- endif -%}
+            {%- endfor -%}
+
+            {#--- Determine what to output based on actual input type ---#}
+            {%- if ns.has_text_input -%}
+                {#--- Main input is text, so output the text content ---#}
+                {{- ns.text_content | trim -}}
+            {%- else -%}
+                {#--- Main input is image or <image> placeholder ---#}
+                {%- set ns2 = namespace(found_image=false) -%}
+                {%- for content in message['content'] -%}
+                    {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}
+                        {{- image_placeholder | trim -}}
+                        {%- set ns2.found_image = true -%}
+                    {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}
+                        {#--- Keep compatibility with <image> for now ---#}
+                        {{- image_placeholder | trim -}}
+                        {%- set ns2.found_image = true -%}
+                    {%- elif content is string and content == '<image>' and not ns2.found_image -%}
+                        {#--- Keep compatibility with <image> for now ---#}
+                        {{- image_placeholder | trim -}}
+                        {%- set ns2.found_image = true -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+        {%- endif -%}
+        {{- '<|im_end|>
+'}}
+
+    {%- elif message['role'] == 'assistant' -%}
+        {{- '<|im_start|>assistant
+' -}}
+        {%- if message['content'] is string -%}
+            {{- message['content'] | trim -}}
+        {%- elif message['content'] is iterable and message['content'] is not string -%}
+            {%- for content in message['content'] -%}
+                {%- if content is mapping and content.get('type') == 'text' -%}
+                    {{- content['text'] | trim -}}
+                {%- elif content is string -%}
+                    {{- content | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {{- '<|im_end|>
+' -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- '<|im_start|>assistant
+' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,93 @@
+{
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "dtype": "float16",
+  "image_token_id": 151655,
+  "model_type": "qwen2_vl",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "float16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_vl_text",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_theta": 1000000.0,
+      "rope_type": "default",
+      "type": "default"
+    },
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float16",
+    "embed_dim": 1280,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1536,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "mlp_ratio": 4,
+    "model_type": "qwen2_vl",
+    "num_heads": 16,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "5.3.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc31d2637c8e852752d84b10d1777642de7e0126a3653a42acaa34b98876686
+size 1991827912

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b5faea7d0c7e5b3bd58e4ff5e195e0133bd3bac0f2e91944610c96a36ded28
+size 1987711664

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050654116f13a2c834e3b2f9bd0bf28f0bff2fa1853e40407bc7289a084cb957
+size 438510032

model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+  "metadata": {
+    "total_parameters": 2208985600,
+    "total_size": 4417971200
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.norm1.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.norm2.bias": "model-00003-of-00003.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00002-of-00003.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00002-of-00003.safetensors",
+    "visual.merger.ln_q.bias": "model-00003-of-00003.safetensors",
+    "visual.merger.ln_q.weight": "model-00003-of-00003.safetensors",
+    "visual.merger.mlp.0.bias": "model-00003-of-00003.safetensors",
+    "visual.merger.mlp.0.weight": "model-00003-of-00003.safetensors",
+    "visual.merger.mlp.2.bias": "model-00003-of-00003.safetensors",
+    "visual.merger.mlp.2.weight": "model-00003-of-00003.safetensors",
+    "visual.patch_embed.proj.weight": "model-00003-of-00003.safetensors"
+  }
+}

processor_config.json

@@ -0,0 +1,66 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_pixels": 301056,
+    "merge_size": 2,
+    "min_pixels": 100352,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 301056,
+      "shortest_edge": 100352
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": false,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "max_pixels": 301056,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 100352,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 23000000,
+      "shortest_edge": 200704
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen2VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7aabe7a3b44651592a99607bb33066e6965260336be9218cccd53af161491d
+size 11422060

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "_commit_hash": null,
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "max_length": null,
+  "max_pixels": 301056,
+  "min_pixels": 100352,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}