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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "quantization_config": {
+    "bits": 4,
+    "checkpoint_format": "gptq",
+    "desc_act": false,
+    "group_size": 128,
+    "lm_head": false,
+    "meta": {
+      "act_group_aware": true,
+      "damp_auto_increment": 0.01,
+      "damp_percent": 0.1,
+      "gptaq": false,
+      "gptaq_alpha": 0.25,
+      "mse": 0.0,
+      "quantizer": [
+        "gptqmodel:5.4.0"
+      ],
+      "static_groups": false,
+      "true_sequential": true,
+      "uri": "https://github.com/modelcloud/gptqmodel"
+    },
+    "pack_dtype": "int32",
+    "pack_impl": "cpu",
+    "quant_method": "gptq",
+    "sym": true
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee426ef5b774cb1afc331d9c5234d88e98b19dc6e66e77d89f02123032e0081
+size 4293927973

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e2e80a5e19ab6359d886787b027414a6ee9611bc69ea7644d59b2d9be4ccc7
+size 2962823089

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

quant_log.csv

@@ -0,0 +1,253 @@
+layer,module,loss,samples,damp,time
+0,self_attn.q_proj,0.0000000460,0.10000,1.909
+0,self_attn.v_proj,0.0000000112,0.10000,1.931
+0,self_attn.k_proj,0.0000000146,0.10000,1.938
+0,self_attn.o_proj,0.0000000788,0.10000,0.737
+0,mlp.up_proj,0.0000119632,0.10000,1.267
+0,mlp.gate_proj,0.0000139261,0.10000,1.266
+0,mlp.down_proj,0.0000061775,0.10000,2.526
+1,self_attn.q_proj,0.0000002586,0.10000,1.851
+1,self_attn.k_proj,0.0000000753,0.10000,1.882
+1,self_attn.v_proj,0.0000000825,0.10000,1.882
+1,self_attn.o_proj,0.0000002652,0.10000,0.745
+1,mlp.gate_proj,0.0003098994,0.10000,1.294
+1,mlp.up_proj,0.0001237676,0.10000,1.300
+1,mlp.down_proj,0.0000019334,0.10000,2.495
+2,self_attn.q_proj,0.0000004842,0.10000,1.831
+2,self_attn.v_proj,0.0000001414,0.10000,1.861
+2,self_attn.k_proj,0.0000001452,0.10000,1.864
+2,self_attn.o_proj,0.0000002143,0.10000,0.735
+2,mlp.gate_proj,0.0005847825,0.10000,1.263
+2,mlp.up_proj,0.0004523424,0.10000,1.267
+2,mlp.down_proj,0.0000011912,0.10000,2.517
+3,self_attn.v_proj,0.0000002465,0.10000,1.899
+3,self_attn.q_proj,0.0000008192,0.10000,1.912
+3,self_attn.k_proj,0.0000002269,0.10000,1.915
+3,self_attn.o_proj,0.0000003573,0.10000,0.738
+3,mlp.gate_proj,0.0005487681,0.10000,1.266
+3,mlp.up_proj,0.0002771917,0.10000,1.268
+3,mlp.down_proj,0.0000021262,0.10000,2.502
+4,self_attn.q_proj,0.0000013610,0.10000,1.828
+4,self_attn.v_proj,0.0000003986,0.10000,1.857
+4,self_attn.k_proj,0.0000003839,0.10000,1.862
+4,self_attn.o_proj,0.0000004117,0.10000,0.729
+4,mlp.gate_proj,0.0004989409,0.10000,1.261
+4,mlp.up_proj,0.0002066679,0.10000,1.261
+4,mlp.down_proj,0.0000041612,0.10000,2.514
+5,self_attn.q_proj,0.0000013875,0.10000,1.854
+5,self_attn.k_proj,0.0000003750,0.10000,1.876
+5,self_attn.v_proj,0.0000004012,0.10000,1.883
+5,self_attn.o_proj,0.0000005539,0.10000,0.731
+5,mlp.gate_proj,0.0001884385,0.10000,1.269
+5,mlp.up_proj,0.0000897748,0.10000,1.276
+5,mlp.down_proj,0.0000058068,0.10000,2.502
+6,self_attn.q_proj,0.0000024079,0.10000,1.836
+6,self_attn.v_proj,0.0000007896,0.10000,1.847
+6,self_attn.k_proj,0.0000006000,0.10000,1.854
+6,self_attn.o_proj,0.0000020132,0.10000,0.736
+6,mlp.gate_proj,0.0001694612,0.10000,1.263
+6,mlp.up_proj,0.0000947139,0.10000,1.269
+6,mlp.down_proj,0.0043268129,0.10000,2.510
+7,self_attn.q_proj,0.0000055269,0.10000,1.849
+7,self_attn.k_proj,0.0000015464,0.10000,1.871
+7,self_attn.v_proj,0.0000017972,0.10000,1.880
+7,self_attn.o_proj,0.0000010108,0.10000,0.731
+7,mlp.up_proj,0.0000909494,0.10000,1.268
+7,mlp.gate_proj,0.0001561245,0.10000,1.269
+7,mlp.down_proj,0.0000075725,0.10000,2.494
+8,self_attn.q_proj,0.0000077203,0.10000,1.834
+8,self_attn.v_proj,0.0000024023,0.10000,1.871
+8,self_attn.k_proj,0.0000020989,0.10000,1.880
+8,self_attn.o_proj,0.0000023099,0.10000,0.730
+8,mlp.up_proj,0.0000628675,0.10000,1.263
+8,mlp.gate_proj,0.0000726722,0.10000,1.270
+8,mlp.down_proj,0.0000126738,0.10000,2.515
+9,self_attn.q_proj,0.0000099998,0.10000,1.852
+9,self_attn.v_proj,0.0000031719,0.10000,1.864
+9,self_attn.k_proj,0.0000029413,0.10000,1.875
+9,self_attn.o_proj,0.0000027857,0.10000,0.732
+9,mlp.gate_proj,0.0001144534,0.10000,1.260
+9,mlp.up_proj,0.0000831869,0.10000,1.266
+9,mlp.down_proj,0.0000163596,0.10000,2.522
+10,self_attn.q_proj,0.0000192783,0.10000,1.838
+10,self_attn.v_proj,0.0000060883,0.10000,1.849
+10,self_attn.k_proj,0.0000052546,0.10000,1.860
+10,self_attn.o_proj,0.0000042604,0.10000,0.730
+10,mlp.gate_proj,0.0001076515,0.10000,1.263
+10,mlp.up_proj,0.0000828841,0.10000,1.262
+10,mlp.down_proj,0.0000169618,0.10000,2.554
+11,self_attn.q_proj,0.0000102978,0.10000,1.850
+11,self_attn.k_proj,0.0000030463,0.10000,1.879
+11,self_attn.v_proj,0.0000031425,0.10000,1.879
+11,self_attn.o_proj,0.0000044318,0.10000,0.733
+11,mlp.gate_proj,0.0001004500,0.10000,1.273
+11,mlp.up_proj,0.0000844784,0.10000,1.274
+11,mlp.down_proj,0.0000162641,0.10000,2.504
+12,self_attn.q_proj,0.0000117331,0.10000,1.837
+12,self_attn.v_proj,0.0000037495,0.10000,1.852
+12,self_attn.k_proj,0.0000033535,0.10000,1.868
+12,self_attn.o_proj,0.0000041830,0.10000,0.731
+12,mlp.gate_proj,0.0000952661,0.10000,1.270
+12,mlp.up_proj,0.0000862941,0.10000,1.275
+12,mlp.down_proj,0.0000156788,0.10000,2.523
+13,self_attn.q_proj,0.0000098528,0.10000,1.839
+13,self_attn.k_proj,0.0000027026,0.10000,1.872
+13,self_attn.v_proj,0.0000028914,0.10000,1.874
+13,self_attn.o_proj,0.0000035654,0.10000,0.733
+13,mlp.up_proj,0.0000889160,0.10000,1.281
+13,mlp.gate_proj,0.0000912081,0.10000,1.288
+13,mlp.down_proj,0.0000170124,0.10000,2.504
+14,self_attn.q_proj,0.0000169375,0.10000,1.835
+14,self_attn.v_proj,0.0000050256,0.10000,1.869
+14,self_attn.k_proj,0.0000045723,0.10000,1.877
+14,self_attn.o_proj,0.0000073589,0.10000,0.742
+14,mlp.up_proj,0.0000884304,0.10000,1.262
+14,mlp.gate_proj,0.0000897608,0.10000,1.268
+14,mlp.down_proj,0.0000161341,0.10000,2.563
+15,self_attn.q_proj,0.0000172137,0.10000,1.826
+15,self_attn.k_proj,0.0000047808,0.10000,1.856
+15,self_attn.v_proj,0.0000049182,0.10000,1.856
+15,self_attn.o_proj,0.0000069495,0.10000,0.729
+15,mlp.gate_proj,0.0000842192,0.10000,1.264
+15,mlp.up_proj,0.0000866066,0.10000,1.267
+15,mlp.down_proj,0.0000161766,0.10000,2.511
+16,self_attn.q_proj,0.0000283130,0.10000,1.828
+16,self_attn.v_proj,0.0000086190,0.10000,1.853
+16,self_attn.k_proj,0.0000073407,0.10000,1.859
+16,self_attn.o_proj,0.0000081478,0.10000,0.733
+16,mlp.gate_proj,0.0000923603,0.10000,1.268
+16,mlp.up_proj,0.0000913179,0.10000,1.271
+16,mlp.down_proj,0.0000170525,0.10000,2.512
+17,self_attn.q_proj,0.0000262860,0.10000,1.838
+17,self_attn.k_proj,0.0000066341,0.10000,1.858
+17,self_attn.v_proj,0.0000074557,0.10000,1.866
+17,self_attn.o_proj,0.0000094712,0.10000,0.728
+17,mlp.gate_proj,0.0000864357,0.10000,1.273
+17,mlp.up_proj,0.0000881547,0.10000,1.276
+17,mlp.down_proj,0.0000177982,0.10000,2.512
+18,self_attn.q_proj,0.0000321468,0.10000,1.827
+18,self_attn.k_proj,0.0000086371,0.10000,1.858
+18,self_attn.v_proj,0.0000097400,0.10000,1.860
+18,self_attn.o_proj,0.0000137180,0.10000,0.730
+18,mlp.up_proj,0.0001054220,0.10000,1.264
+18,mlp.gate_proj,0.0001032740,0.10000,1.269
+18,mlp.down_proj,0.0000249287,0.10000,2.582
+19,self_attn.q_proj,0.0000652757,0.10000,1.832
+19,self_attn.k_proj,0.0000170230,0.10000,1.862
+19,self_attn.v_proj,0.0000185613,0.10000,1.868
+19,self_attn.o_proj,0.0000139371,0.10000,0.730
+19,mlp.gate_proj,0.0001154005,0.10000,1.260
+19,mlp.up_proj,0.0001191767,0.10000,1.266
+19,mlp.down_proj,0.0000319580,0.10000,2.514
+20,self_attn.q_proj,0.0000590725,0.10000,1.835
+20,self_attn.v_proj,0.0000171313,0.10000,1.836
+20,self_attn.k_proj,0.0000135838,0.10000,1.853
+20,self_attn.o_proj,0.0000140515,0.10000,0.733
+20,mlp.gate_proj,0.0001199461,0.10000,1.272
+20,mlp.up_proj,0.0001253672,0.10000,1.279
+20,mlp.down_proj,0.0000345492,0.10000,2.516
+21,self_attn.q_proj,0.0000877000,0.10000,1.841
+21,self_attn.k_proj,0.0000207046,0.10000,1.858
+21,self_attn.v_proj,0.0000278125,0.10000,1.865
+21,self_attn.o_proj,0.0000181872,0.10000,0.744
+21,mlp.up_proj,0.0001532922,0.10000,1.263
+21,mlp.gate_proj,0.0001483141,0.10000,1.264
+21,mlp.down_proj,0.0000463515,0.10000,2.512
+22,self_attn.q_proj,0.0001692149,0.10000,1.830
+22,self_attn.k_proj,0.0000403577,0.10000,1.846
+22,self_attn.v_proj,0.0000530100,0.10000,1.849
+22,self_attn.o_proj,0.0000301380,0.10000,0.737
+22,mlp.up_proj,0.0001755515,0.10000,1.284
+22,mlp.gate_proj,0.0001730623,0.10000,1.287
+22,mlp.down_proj,0.0000724474,0.10000,2.520
+23,self_attn.q_proj,0.0001803910,0.10000,1.835
+23,self_attn.k_proj,0.0000405199,0.10000,1.847
+23,self_attn.v_proj,0.0000598627,0.10000,1.854
+23,self_attn.o_proj,0.0000463306,0.10000,0.741
+23,mlp.up_proj,0.0002044011,0.10000,1.265
+23,mlp.gate_proj,0.0002059745,0.10000,1.267
+23,mlp.down_proj,0.0001013227,0.10000,2.494
+24,self_attn.q_proj,0.0003566299,0.10000,1.832
+24,self_attn.v_proj,0.0001226614,0.10000,1.850
+24,self_attn.k_proj,0.0000764897,0.10000,1.854
+24,self_attn.o_proj,0.0000536433,0.10000,0.741
+24,mlp.gate_proj,0.0002422834,0.10000,1.268
+24,mlp.up_proj,0.0002408803,0.10000,1.276
+24,mlp.down_proj,0.0001374037,0.10000,2.511
+25,self_attn.q_proj,0.0002585693,0.10000,1.851
+25,self_attn.v_proj,0.0000865364,0.10000,1.861
+25,self_attn.k_proj,0.0000622373,0.10000,1.868
+25,self_attn.o_proj,0.0000261037,0.10000,0.749
+25,mlp.gate_proj,0.0002719650,0.10000,1.269
+25,mlp.up_proj,0.0002682968,0.10000,1.273
+25,mlp.down_proj,0.0001554834,0.10000,2.505
+26,self_attn.q_proj,0.0004138489,0.10000,1.849
+26,self_attn.k_proj,0.0000947415,0.10000,1.868
+26,self_attn.v_proj,0.0001315248,0.10000,1.875
+26,self_attn.o_proj,0.0000444673,0.10000,0.762
+26,mlp.gate_proj,0.0003301754,0.10000,1.323
+26,mlp.up_proj,0.0003314627,0.10000,1.330
+26,mlp.down_proj,0.0002004149,0.10000,2.510
+27,self_attn.q_proj,0.0005140213,0.10000,1.834
+27,self_attn.v_proj,0.0001651335,0.10000,1.854
+27,self_attn.k_proj,0.0001152000,0.10000,1.860
+27,self_attn.o_proj,0.0000357773,0.10000,0.750
+27,mlp.gate_proj,0.0003852402,0.10000,1.268
+27,mlp.up_proj,0.0003931775,0.10000,1.271
+27,mlp.down_proj,0.0002928375,0.10000,2.511
+28,self_attn.q_proj,0.0006429203,0.10000,1.838
+28,self_attn.k_proj,0.0001542942,0.10000,1.853
+28,self_attn.v_proj,0.0002002135,0.10000,1.858
+28,self_attn.o_proj,0.0000683038,0.10000,0.751
+28,mlp.gate_proj,0.0004701391,0.10000,1.277
+28,mlp.up_proj,0.0004910136,0.10000,1.277
+28,mlp.down_proj,0.0004325272,0.10000,2.505
+29,self_attn.q_proj,0.0014884251,0.10000,1.840
+29,self_attn.v_proj,0.0004984688,0.10000,1.857
+29,self_attn.k_proj,0.0003327431,0.10000,1.858
+29,self_attn.o_proj,0.0001098333,0.10000,0.745
+29,mlp.gate_proj,0.0005864102,0.10000,1.266
+29,mlp.up_proj,0.0006399369,0.10000,1.266
+29,mlp.down_proj,0.0006130929,0.10000,2.510
+30,self_attn.q_proj,0.0016591532,0.10000,1.941
+30,self_attn.k_proj,0.0004269033,0.10000,1.967
+30,self_attn.v_proj,0.0006399306,0.10000,1.967
+30,self_attn.o_proj,0.0000966583,0.10000,0.764
+30,mlp.up_proj,0.0007551041,0.10000,1.289
+30,mlp.gate_proj,0.0006748903,0.10000,1.299
+30,mlp.down_proj,0.0008542519,0.10000,2.516
+31,self_attn.q_proj,0.0023436447,0.10000,1.846
+31,self_attn.k_proj,0.0005889513,0.10000,1.854
+31,self_attn.v_proj,0.0009138195,0.10000,1.862
+31,self_attn.o_proj,0.0001454709,0.10000,0.749
+31,mlp.up_proj,0.0008670128,0.10000,1.269
+31,mlp.gate_proj,0.0007464102,0.10000,1.271
+31,mlp.down_proj,0.0012083045,0.10000,2.508
+32,self_attn.q_proj,0.0035290810,0.10000,1.850
+32,self_attn.k_proj,0.0008717434,0.10000,1.868
+32,self_attn.v_proj,0.0014363856,0.10000,1.875
+32,self_attn.o_proj,0.0002042462,0.10000,0.749
+32,mlp.gate_proj,0.0008403051,0.10000,1.266
+32,mlp.up_proj,0.0009951350,0.10000,1.272
+32,mlp.down_proj,0.0015861297,0.10000,2.507
+33,self_attn.q_proj,0.0064872053,0.10000,1.830
+33,self_attn.v_proj,0.0027781121,0.10000,1.849
+33,self_attn.k_proj,0.0013904978,0.10000,1.860
+33,self_attn.o_proj,0.0003030629,0.10000,0.751
+33,mlp.gate_proj,0.0009790592,0.10000,1.261
+33,mlp.up_proj,0.0011809722,0.10000,1.264
+33,mlp.down_proj,0.0022232788,0.10000,2.496
+34,self_attn.k_proj,0.0015066362,0.10000,1.906
+34,self_attn.q_proj,0.0063627102,0.10000,1.917
+34,self_attn.v_proj,0.0028609966,0.10000,1.932
+34,self_attn.o_proj,0.0008517727,0.10000,0.764
+34,mlp.gate_proj,0.0012525847,0.10000,1.264
+34,mlp.up_proj,0.0014389654,0.10000,1.269
+34,mlp.down_proj,0.0032939305,0.10000,2.521
+35,self_attn.q_proj,0.0030453914,0.10000,1.825
+35,self_attn.v_proj,0.0011508923,0.10000,1.840
+35,self_attn.k_proj,0.0007816510,0.10000,1.850
+35,self_attn.o_proj,0.0009201406,0.10000,0.747
+35,mlp.up_proj,0.0026738517,0.10000,1.283
+35,mlp.gate_proj,0.0023156200,0.10000,1.288
+35,mlp.down_proj,0.0139715316,0.10000,2.495

quantize_config.json

@@ -0,0 +1,25 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "desc_act": false,
+  "sym": true,
+  "lm_head": false,
+  "quant_method": "gptq",
+  "checkpoint_format": "gptq",
+  "pack_dtype": "int32",
+  "meta": {
+    "quantizer": [
+      "gptqmodel:5.4.0"
+    ],
+    "uri": "https://github.com/modelcloud/gptqmodel",
+    "damp_percent": 0.1,
+    "damp_auto_increment": 0.01,
+    "static_groups": false,
+    "true_sequential": true,
+    "mse": 0.0,
+    "gptaq": false,
+    "gptaq_alpha": 0.25,
+    "act_group_aware": true
+  },
+  "pack_impl": "cpu"
+}

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "_commit_hash": null
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}