Instructions to use sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4") model = AutoModelForMultimodalLM.from_pretrained("sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4
- SGLang
How to use sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4 with Docker Model Runner:
docker model run hf.co/sitatech/Qwen3-VL-8B-Instruct-GPTQ-Int4
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +199 -0
- added_tokens.json +28 -0
- chat_template.jinja +120 -0
- config.json +89 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +39 -0
- quant_log.csv +253 -0
- quantize_config.json +25 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags: []
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"quantization_config": {
|
| 9 |
+
"bits": 4,
|
| 10 |
+
"checkpoint_format": "gptq",
|
| 11 |
+
"desc_act": false,
|
| 12 |
+
"group_size": 128,
|
| 13 |
+
"lm_head": false,
|
| 14 |
+
"meta": {
|
| 15 |
+
"act_group_aware": true,
|
| 16 |
+
"damp_auto_increment": 0.01,
|
| 17 |
+
"damp_percent": 0.1,
|
| 18 |
+
"gptaq": false,
|
| 19 |
+
"gptaq_alpha": 0.25,
|
| 20 |
+
"mse": 0.0,
|
| 21 |
+
"quantizer": [
|
| 22 |
+
"gptqmodel:5.4.0"
|
| 23 |
+
],
|
| 24 |
+
"static_groups": false,
|
| 25 |
+
"true_sequential": true,
|
| 26 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 27 |
+
},
|
| 28 |
+
"pack_dtype": "int32",
|
| 29 |
+
"pack_impl": "cpu",
|
| 30 |
+
"quant_method": "gptq",
|
| 31 |
+
"sym": true
|
| 32 |
+
},
|
| 33 |
+
"text_config": {
|
| 34 |
+
"attention_bias": false,
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"bos_token_id": 151643,
|
| 37 |
+
"dtype": "bfloat16",
|
| 38 |
+
"eos_token_id": 151645,
|
| 39 |
+
"head_dim": 128,
|
| 40 |
+
"hidden_act": "silu",
|
| 41 |
+
"hidden_size": 4096,
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 12288,
|
| 44 |
+
"max_position_embeddings": 262144,
|
| 45 |
+
"model_type": "qwen3_vl_text",
|
| 46 |
+
"num_attention_heads": 32,
|
| 47 |
+
"num_hidden_layers": 36,
|
| 48 |
+
"num_key_value_heads": 8,
|
| 49 |
+
"rms_norm_eps": 1e-06,
|
| 50 |
+
"rope_scaling": {
|
| 51 |
+
"mrope_interleaved": true,
|
| 52 |
+
"mrope_section": [
|
| 53 |
+
24,
|
| 54 |
+
20,
|
| 55 |
+
20
|
| 56 |
+
],
|
| 57 |
+
"rope_type": "default"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 5000000,
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 151936
|
| 62 |
+
},
|
| 63 |
+
"tie_word_embeddings": false,
|
| 64 |
+
"transformers_version": "4.57.1",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"video_token_id": 151656,
|
| 67 |
+
"vision_config": {
|
| 68 |
+
"deepstack_visual_indexes": [
|
| 69 |
+
8,
|
| 70 |
+
16,
|
| 71 |
+
24
|
| 72 |
+
],
|
| 73 |
+
"depth": 27,
|
| 74 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 75 |
+
"hidden_size": 1152,
|
| 76 |
+
"in_channels": 3,
|
| 77 |
+
"initializer_range": 0.02,
|
| 78 |
+
"intermediate_size": 4304,
|
| 79 |
+
"model_type": "qwen3_vl",
|
| 80 |
+
"num_heads": 16,
|
| 81 |
+
"num_position_embeddings": 2304,
|
| 82 |
+
"out_hidden_size": 4096,
|
| 83 |
+
"patch_size": 16,
|
| 84 |
+
"spatial_merge_size": 2,
|
| 85 |
+
"temporal_patch_size": 2
|
| 86 |
+
},
|
| 87 |
+
"vision_end_token_id": 151653,
|
| 88 |
+
"vision_start_token_id": 151652
|
| 89 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"temperature": 0.7,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"transformers_version": "4.57.1"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eee426ef5b774cb1afc331d9c5234d88e98b19dc6e66e77d89f02123032e0081
|
| 3 |
+
size 4293927973
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0e2e80a5e19ab6359d886787b027414a6ee9611bc69ea7644d59b2d9be4ccc7
|
| 3 |
+
size 2962823089
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
quant_log.csv
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
layer,module,loss,samples,damp,time
|
| 2 |
+
0,self_attn.q_proj,0.0000000460,0.10000,1.909
|
| 3 |
+
0,self_attn.v_proj,0.0000000112,0.10000,1.931
|
| 4 |
+
0,self_attn.k_proj,0.0000000146,0.10000,1.938
|
| 5 |
+
0,self_attn.o_proj,0.0000000788,0.10000,0.737
|
| 6 |
+
0,mlp.up_proj,0.0000119632,0.10000,1.267
|
| 7 |
+
0,mlp.gate_proj,0.0000139261,0.10000,1.266
|
| 8 |
+
0,mlp.down_proj,0.0000061775,0.10000,2.526
|
| 9 |
+
1,self_attn.q_proj,0.0000002586,0.10000,1.851
|
| 10 |
+
1,self_attn.k_proj,0.0000000753,0.10000,1.882
|
| 11 |
+
1,self_attn.v_proj,0.0000000825,0.10000,1.882
|
| 12 |
+
1,self_attn.o_proj,0.0000002652,0.10000,0.745
|
| 13 |
+
1,mlp.gate_proj,0.0003098994,0.10000,1.294
|
| 14 |
+
1,mlp.up_proj,0.0001237676,0.10000,1.300
|
| 15 |
+
1,mlp.down_proj,0.0000019334,0.10000,2.495
|
| 16 |
+
2,self_attn.q_proj,0.0000004842,0.10000,1.831
|
| 17 |
+
2,self_attn.v_proj,0.0000001414,0.10000,1.861
|
| 18 |
+
2,self_attn.k_proj,0.0000001452,0.10000,1.864
|
| 19 |
+
2,self_attn.o_proj,0.0000002143,0.10000,0.735
|
| 20 |
+
2,mlp.gate_proj,0.0005847825,0.10000,1.263
|
| 21 |
+
2,mlp.up_proj,0.0004523424,0.10000,1.267
|
| 22 |
+
2,mlp.down_proj,0.0000011912,0.10000,2.517
|
| 23 |
+
3,self_attn.v_proj,0.0000002465,0.10000,1.899
|
| 24 |
+
3,self_attn.q_proj,0.0000008192,0.10000,1.912
|
| 25 |
+
3,self_attn.k_proj,0.0000002269,0.10000,1.915
|
| 26 |
+
3,self_attn.o_proj,0.0000003573,0.10000,0.738
|
| 27 |
+
3,mlp.gate_proj,0.0005487681,0.10000,1.266
|
| 28 |
+
3,mlp.up_proj,0.0002771917,0.10000,1.268
|
| 29 |
+
3,mlp.down_proj,0.0000021262,0.10000,2.502
|
| 30 |
+
4,self_attn.q_proj,0.0000013610,0.10000,1.828
|
| 31 |
+
4,self_attn.v_proj,0.0000003986,0.10000,1.857
|
| 32 |
+
4,self_attn.k_proj,0.0000003839,0.10000,1.862
|
| 33 |
+
4,self_attn.o_proj,0.0000004117,0.10000,0.729
|
| 34 |
+
4,mlp.gate_proj,0.0004989409,0.10000,1.261
|
| 35 |
+
4,mlp.up_proj,0.0002066679,0.10000,1.261
|
| 36 |
+
4,mlp.down_proj,0.0000041612,0.10000,2.514
|
| 37 |
+
5,self_attn.q_proj,0.0000013875,0.10000,1.854
|
| 38 |
+
5,self_attn.k_proj,0.0000003750,0.10000,1.876
|
| 39 |
+
5,self_attn.v_proj,0.0000004012,0.10000,1.883
|
| 40 |
+
5,self_attn.o_proj,0.0000005539,0.10000,0.731
|
| 41 |
+
5,mlp.gate_proj,0.0001884385,0.10000,1.269
|
| 42 |
+
5,mlp.up_proj,0.0000897748,0.10000,1.276
|
| 43 |
+
5,mlp.down_proj,0.0000058068,0.10000,2.502
|
| 44 |
+
6,self_attn.q_proj,0.0000024079,0.10000,1.836
|
| 45 |
+
6,self_attn.v_proj,0.0000007896,0.10000,1.847
|
| 46 |
+
6,self_attn.k_proj,0.0000006000,0.10000,1.854
|
| 47 |
+
6,self_attn.o_proj,0.0000020132,0.10000,0.736
|
| 48 |
+
6,mlp.gate_proj,0.0001694612,0.10000,1.263
|
| 49 |
+
6,mlp.up_proj,0.0000947139,0.10000,1.269
|
| 50 |
+
6,mlp.down_proj,0.0043268129,0.10000,2.510
|
| 51 |
+
7,self_attn.q_proj,0.0000055269,0.10000,1.849
|
| 52 |
+
7,self_attn.k_proj,0.0000015464,0.10000,1.871
|
| 53 |
+
7,self_attn.v_proj,0.0000017972,0.10000,1.880
|
| 54 |
+
7,self_attn.o_proj,0.0000010108,0.10000,0.731
|
| 55 |
+
7,mlp.up_proj,0.0000909494,0.10000,1.268
|
| 56 |
+
7,mlp.gate_proj,0.0001561245,0.10000,1.269
|
| 57 |
+
7,mlp.down_proj,0.0000075725,0.10000,2.494
|
| 58 |
+
8,self_attn.q_proj,0.0000077203,0.10000,1.834
|
| 59 |
+
8,self_attn.v_proj,0.0000024023,0.10000,1.871
|
| 60 |
+
8,self_attn.k_proj,0.0000020989,0.10000,1.880
|
| 61 |
+
8,self_attn.o_proj,0.0000023099,0.10000,0.730
|
| 62 |
+
8,mlp.up_proj,0.0000628675,0.10000,1.263
|
| 63 |
+
8,mlp.gate_proj,0.0000726722,0.10000,1.270
|
| 64 |
+
8,mlp.down_proj,0.0000126738,0.10000,2.515
|
| 65 |
+
9,self_attn.q_proj,0.0000099998,0.10000,1.852
|
| 66 |
+
9,self_attn.v_proj,0.0000031719,0.10000,1.864
|
| 67 |
+
9,self_attn.k_proj,0.0000029413,0.10000,1.875
|
| 68 |
+
9,self_attn.o_proj,0.0000027857,0.10000,0.732
|
| 69 |
+
9,mlp.gate_proj,0.0001144534,0.10000,1.260
|
| 70 |
+
9,mlp.up_proj,0.0000831869,0.10000,1.266
|
| 71 |
+
9,mlp.down_proj,0.0000163596,0.10000,2.522
|
| 72 |
+
10,self_attn.q_proj,0.0000192783,0.10000,1.838
|
| 73 |
+
10,self_attn.v_proj,0.0000060883,0.10000,1.849
|
| 74 |
+
10,self_attn.k_proj,0.0000052546,0.10000,1.860
|
| 75 |
+
10,self_attn.o_proj,0.0000042604,0.10000,0.730
|
| 76 |
+
10,mlp.gate_proj,0.0001076515,0.10000,1.263
|
| 77 |
+
10,mlp.up_proj,0.0000828841,0.10000,1.262
|
| 78 |
+
10,mlp.down_proj,0.0000169618,0.10000,2.554
|
| 79 |
+
11,self_attn.q_proj,0.0000102978,0.10000,1.850
|
| 80 |
+
11,self_attn.k_proj,0.0000030463,0.10000,1.879
|
| 81 |
+
11,self_attn.v_proj,0.0000031425,0.10000,1.879
|
| 82 |
+
11,self_attn.o_proj,0.0000044318,0.10000,0.733
|
| 83 |
+
11,mlp.gate_proj,0.0001004500,0.10000,1.273
|
| 84 |
+
11,mlp.up_proj,0.0000844784,0.10000,1.274
|
| 85 |
+
11,mlp.down_proj,0.0000162641,0.10000,2.504
|
| 86 |
+
12,self_attn.q_proj,0.0000117331,0.10000,1.837
|
| 87 |
+
12,self_attn.v_proj,0.0000037495,0.10000,1.852
|
| 88 |
+
12,self_attn.k_proj,0.0000033535,0.10000,1.868
|
| 89 |
+
12,self_attn.o_proj,0.0000041830,0.10000,0.731
|
| 90 |
+
12,mlp.gate_proj,0.0000952661,0.10000,1.270
|
| 91 |
+
12,mlp.up_proj,0.0000862941,0.10000,1.275
|
| 92 |
+
12,mlp.down_proj,0.0000156788,0.10000,2.523
|
| 93 |
+
13,self_attn.q_proj,0.0000098528,0.10000,1.839
|
| 94 |
+
13,self_attn.k_proj,0.0000027026,0.10000,1.872
|
| 95 |
+
13,self_attn.v_proj,0.0000028914,0.10000,1.874
|
| 96 |
+
13,self_attn.o_proj,0.0000035654,0.10000,0.733
|
| 97 |
+
13,mlp.up_proj,0.0000889160,0.10000,1.281
|
| 98 |
+
13,mlp.gate_proj,0.0000912081,0.10000,1.288
|
| 99 |
+
13,mlp.down_proj,0.0000170124,0.10000,2.504
|
| 100 |
+
14,self_attn.q_proj,0.0000169375,0.10000,1.835
|
| 101 |
+
14,self_attn.v_proj,0.0000050256,0.10000,1.869
|
| 102 |
+
14,self_attn.k_proj,0.0000045723,0.10000,1.877
|
| 103 |
+
14,self_attn.o_proj,0.0000073589,0.10000,0.742
|
| 104 |
+
14,mlp.up_proj,0.0000884304,0.10000,1.262
|
| 105 |
+
14,mlp.gate_proj,0.0000897608,0.10000,1.268
|
| 106 |
+
14,mlp.down_proj,0.0000161341,0.10000,2.563
|
| 107 |
+
15,self_attn.q_proj,0.0000172137,0.10000,1.826
|
| 108 |
+
15,self_attn.k_proj,0.0000047808,0.10000,1.856
|
| 109 |
+
15,self_attn.v_proj,0.0000049182,0.10000,1.856
|
| 110 |
+
15,self_attn.o_proj,0.0000069495,0.10000,0.729
|
| 111 |
+
15,mlp.gate_proj,0.0000842192,0.10000,1.264
|
| 112 |
+
15,mlp.up_proj,0.0000866066,0.10000,1.267
|
| 113 |
+
15,mlp.down_proj,0.0000161766,0.10000,2.511
|
| 114 |
+
16,self_attn.q_proj,0.0000283130,0.10000,1.828
|
| 115 |
+
16,self_attn.v_proj,0.0000086190,0.10000,1.853
|
| 116 |
+
16,self_attn.k_proj,0.0000073407,0.10000,1.859
|
| 117 |
+
16,self_attn.o_proj,0.0000081478,0.10000,0.733
|
| 118 |
+
16,mlp.gate_proj,0.0000923603,0.10000,1.268
|
| 119 |
+
16,mlp.up_proj,0.0000913179,0.10000,1.271
|
| 120 |
+
16,mlp.down_proj,0.0000170525,0.10000,2.512
|
| 121 |
+
17,self_attn.q_proj,0.0000262860,0.10000,1.838
|
| 122 |
+
17,self_attn.k_proj,0.0000066341,0.10000,1.858
|
| 123 |
+
17,self_attn.v_proj,0.0000074557,0.10000,1.866
|
| 124 |
+
17,self_attn.o_proj,0.0000094712,0.10000,0.728
|
| 125 |
+
17,mlp.gate_proj,0.0000864357,0.10000,1.273
|
| 126 |
+
17,mlp.up_proj,0.0000881547,0.10000,1.276
|
| 127 |
+
17,mlp.down_proj,0.0000177982,0.10000,2.512
|
| 128 |
+
18,self_attn.q_proj,0.0000321468,0.10000,1.827
|
| 129 |
+
18,self_attn.k_proj,0.0000086371,0.10000,1.858
|
| 130 |
+
18,self_attn.v_proj,0.0000097400,0.10000,1.860
|
| 131 |
+
18,self_attn.o_proj,0.0000137180,0.10000,0.730
|
| 132 |
+
18,mlp.up_proj,0.0001054220,0.10000,1.264
|
| 133 |
+
18,mlp.gate_proj,0.0001032740,0.10000,1.269
|
| 134 |
+
18,mlp.down_proj,0.0000249287,0.10000,2.582
|
| 135 |
+
19,self_attn.q_proj,0.0000652757,0.10000,1.832
|
| 136 |
+
19,self_attn.k_proj,0.0000170230,0.10000,1.862
|
| 137 |
+
19,self_attn.v_proj,0.0000185613,0.10000,1.868
|
| 138 |
+
19,self_attn.o_proj,0.0000139371,0.10000,0.730
|
| 139 |
+
19,mlp.gate_proj,0.0001154005,0.10000,1.260
|
| 140 |
+
19,mlp.up_proj,0.0001191767,0.10000,1.266
|
| 141 |
+
19,mlp.down_proj,0.0000319580,0.10000,2.514
|
| 142 |
+
20,self_attn.q_proj,0.0000590725,0.10000,1.835
|
| 143 |
+
20,self_attn.v_proj,0.0000171313,0.10000,1.836
|
| 144 |
+
20,self_attn.k_proj,0.0000135838,0.10000,1.853
|
| 145 |
+
20,self_attn.o_proj,0.0000140515,0.10000,0.733
|
| 146 |
+
20,mlp.gate_proj,0.0001199461,0.10000,1.272
|
| 147 |
+
20,mlp.up_proj,0.0001253672,0.10000,1.279
|
| 148 |
+
20,mlp.down_proj,0.0000345492,0.10000,2.516
|
| 149 |
+
21,self_attn.q_proj,0.0000877000,0.10000,1.841
|
| 150 |
+
21,self_attn.k_proj,0.0000207046,0.10000,1.858
|
| 151 |
+
21,self_attn.v_proj,0.0000278125,0.10000,1.865
|
| 152 |
+
21,self_attn.o_proj,0.0000181872,0.10000,0.744
|
| 153 |
+
21,mlp.up_proj,0.0001532922,0.10000,1.263
|
| 154 |
+
21,mlp.gate_proj,0.0001483141,0.10000,1.264
|
| 155 |
+
21,mlp.down_proj,0.0000463515,0.10000,2.512
|
| 156 |
+
22,self_attn.q_proj,0.0001692149,0.10000,1.830
|
| 157 |
+
22,self_attn.k_proj,0.0000403577,0.10000,1.846
|
| 158 |
+
22,self_attn.v_proj,0.0000530100,0.10000,1.849
|
| 159 |
+
22,self_attn.o_proj,0.0000301380,0.10000,0.737
|
| 160 |
+
22,mlp.up_proj,0.0001755515,0.10000,1.284
|
| 161 |
+
22,mlp.gate_proj,0.0001730623,0.10000,1.287
|
| 162 |
+
22,mlp.down_proj,0.0000724474,0.10000,2.520
|
| 163 |
+
23,self_attn.q_proj,0.0001803910,0.10000,1.835
|
| 164 |
+
23,self_attn.k_proj,0.0000405199,0.10000,1.847
|
| 165 |
+
23,self_attn.v_proj,0.0000598627,0.10000,1.854
|
| 166 |
+
23,self_attn.o_proj,0.0000463306,0.10000,0.741
|
| 167 |
+
23,mlp.up_proj,0.0002044011,0.10000,1.265
|
| 168 |
+
23,mlp.gate_proj,0.0002059745,0.10000,1.267
|
| 169 |
+
23,mlp.down_proj,0.0001013227,0.10000,2.494
|
| 170 |
+
24,self_attn.q_proj,0.0003566299,0.10000,1.832
|
| 171 |
+
24,self_attn.v_proj,0.0001226614,0.10000,1.850
|
| 172 |
+
24,self_attn.k_proj,0.0000764897,0.10000,1.854
|
| 173 |
+
24,self_attn.o_proj,0.0000536433,0.10000,0.741
|
| 174 |
+
24,mlp.gate_proj,0.0002422834,0.10000,1.268
|
| 175 |
+
24,mlp.up_proj,0.0002408803,0.10000,1.276
|
| 176 |
+
24,mlp.down_proj,0.0001374037,0.10000,2.511
|
| 177 |
+
25,self_attn.q_proj,0.0002585693,0.10000,1.851
|
| 178 |
+
25,self_attn.v_proj,0.0000865364,0.10000,1.861
|
| 179 |
+
25,self_attn.k_proj,0.0000622373,0.10000,1.868
|
| 180 |
+
25,self_attn.o_proj,0.0000261037,0.10000,0.749
|
| 181 |
+
25,mlp.gate_proj,0.0002719650,0.10000,1.269
|
| 182 |
+
25,mlp.up_proj,0.0002682968,0.10000,1.273
|
| 183 |
+
25,mlp.down_proj,0.0001554834,0.10000,2.505
|
| 184 |
+
26,self_attn.q_proj,0.0004138489,0.10000,1.849
|
| 185 |
+
26,self_attn.k_proj,0.0000947415,0.10000,1.868
|
| 186 |
+
26,self_attn.v_proj,0.0001315248,0.10000,1.875
|
| 187 |
+
26,self_attn.o_proj,0.0000444673,0.10000,0.762
|
| 188 |
+
26,mlp.gate_proj,0.0003301754,0.10000,1.323
|
| 189 |
+
26,mlp.up_proj,0.0003314627,0.10000,1.330
|
| 190 |
+
26,mlp.down_proj,0.0002004149,0.10000,2.510
|
| 191 |
+
27,self_attn.q_proj,0.0005140213,0.10000,1.834
|
| 192 |
+
27,self_attn.v_proj,0.0001651335,0.10000,1.854
|
| 193 |
+
27,self_attn.k_proj,0.0001152000,0.10000,1.860
|
| 194 |
+
27,self_attn.o_proj,0.0000357773,0.10000,0.750
|
| 195 |
+
27,mlp.gate_proj,0.0003852402,0.10000,1.268
|
| 196 |
+
27,mlp.up_proj,0.0003931775,0.10000,1.271
|
| 197 |
+
27,mlp.down_proj,0.0002928375,0.10000,2.511
|
| 198 |
+
28,self_attn.q_proj,0.0006429203,0.10000,1.838
|
| 199 |
+
28,self_attn.k_proj,0.0001542942,0.10000,1.853
|
| 200 |
+
28,self_attn.v_proj,0.0002002135,0.10000,1.858
|
| 201 |
+
28,self_attn.o_proj,0.0000683038,0.10000,0.751
|
| 202 |
+
28,mlp.gate_proj,0.0004701391,0.10000,1.277
|
| 203 |
+
28,mlp.up_proj,0.0004910136,0.10000,1.277
|
| 204 |
+
28,mlp.down_proj,0.0004325272,0.10000,2.505
|
| 205 |
+
29,self_attn.q_proj,0.0014884251,0.10000,1.840
|
| 206 |
+
29,self_attn.v_proj,0.0004984688,0.10000,1.857
|
| 207 |
+
29,self_attn.k_proj,0.0003327431,0.10000,1.858
|
| 208 |
+
29,self_attn.o_proj,0.0001098333,0.10000,0.745
|
| 209 |
+
29,mlp.gate_proj,0.0005864102,0.10000,1.266
|
| 210 |
+
29,mlp.up_proj,0.0006399369,0.10000,1.266
|
| 211 |
+
29,mlp.down_proj,0.0006130929,0.10000,2.510
|
| 212 |
+
30,self_attn.q_proj,0.0016591532,0.10000,1.941
|
| 213 |
+
30,self_attn.k_proj,0.0004269033,0.10000,1.967
|
| 214 |
+
30,self_attn.v_proj,0.0006399306,0.10000,1.967
|
| 215 |
+
30,self_attn.o_proj,0.0000966583,0.10000,0.764
|
| 216 |
+
30,mlp.up_proj,0.0007551041,0.10000,1.289
|
| 217 |
+
30,mlp.gate_proj,0.0006748903,0.10000,1.299
|
| 218 |
+
30,mlp.down_proj,0.0008542519,0.10000,2.516
|
| 219 |
+
31,self_attn.q_proj,0.0023436447,0.10000,1.846
|
| 220 |
+
31,self_attn.k_proj,0.0005889513,0.10000,1.854
|
| 221 |
+
31,self_attn.v_proj,0.0009138195,0.10000,1.862
|
| 222 |
+
31,self_attn.o_proj,0.0001454709,0.10000,0.749
|
| 223 |
+
31,mlp.up_proj,0.0008670128,0.10000,1.269
|
| 224 |
+
31,mlp.gate_proj,0.0007464102,0.10000,1.271
|
| 225 |
+
31,mlp.down_proj,0.0012083045,0.10000,2.508
|
| 226 |
+
32,self_attn.q_proj,0.0035290810,0.10000,1.850
|
| 227 |
+
32,self_attn.k_proj,0.0008717434,0.10000,1.868
|
| 228 |
+
32,self_attn.v_proj,0.0014363856,0.10000,1.875
|
| 229 |
+
32,self_attn.o_proj,0.0002042462,0.10000,0.749
|
| 230 |
+
32,mlp.gate_proj,0.0008403051,0.10000,1.266
|
| 231 |
+
32,mlp.up_proj,0.0009951350,0.10000,1.272
|
| 232 |
+
32,mlp.down_proj,0.0015861297,0.10000,2.507
|
| 233 |
+
33,self_attn.q_proj,0.0064872053,0.10000,1.830
|
| 234 |
+
33,self_attn.v_proj,0.0027781121,0.10000,1.849
|
| 235 |
+
33,self_attn.k_proj,0.0013904978,0.10000,1.860
|
| 236 |
+
33,self_attn.o_proj,0.0003030629,0.10000,0.751
|
| 237 |
+
33,mlp.gate_proj,0.0009790592,0.10000,1.261
|
| 238 |
+
33,mlp.up_proj,0.0011809722,0.10000,1.264
|
| 239 |
+
33,mlp.down_proj,0.0022232788,0.10000,2.496
|
| 240 |
+
34,self_attn.k_proj,0.0015066362,0.10000,1.906
|
| 241 |
+
34,self_attn.q_proj,0.0063627102,0.10000,1.917
|
| 242 |
+
34,self_attn.v_proj,0.0028609966,0.10000,1.932
|
| 243 |
+
34,self_attn.o_proj,0.0008517727,0.10000,0.764
|
| 244 |
+
34,mlp.gate_proj,0.0012525847,0.10000,1.264
|
| 245 |
+
34,mlp.up_proj,0.0014389654,0.10000,1.269
|
| 246 |
+
34,mlp.down_proj,0.0032939305,0.10000,2.521
|
| 247 |
+
35,self_attn.q_proj,0.0030453914,0.10000,1.825
|
| 248 |
+
35,self_attn.v_proj,0.0011508923,0.10000,1.840
|
| 249 |
+
35,self_attn.k_proj,0.0007816510,0.10000,1.850
|
| 250 |
+
35,self_attn.o_proj,0.0009201406,0.10000,0.747
|
| 251 |
+
35,mlp.up_proj,0.0026738517,0.10000,1.283
|
| 252 |
+
35,mlp.gate_proj,0.0023156200,0.10000,1.288
|
| 253 |
+
35,mlp.down_proj,0.0139715316,0.10000,2.495
|
quantize_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"desc_act": false,
|
| 5 |
+
"sym": true,
|
| 6 |
+
"lm_head": false,
|
| 7 |
+
"quant_method": "gptq",
|
| 8 |
+
"checkpoint_format": "gptq",
|
| 9 |
+
"pack_dtype": "int32",
|
| 10 |
+
"meta": {
|
| 11 |
+
"quantizer": [
|
| 12 |
+
"gptqmodel:5.4.0"
|
| 13 |
+
],
|
| 14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.1,
|
| 16 |
+
"damp_auto_increment": 0.01,
|
| 17 |
+
"static_groups": false,
|
| 18 |
+
"true_sequential": true,
|
| 19 |
+
"mse": 0.0,
|
| 20 |
+
"gptaq": false,
|
| 21 |
+
"gptaq_alpha": 0.25,
|
| 22 |
+
"act_group_aware": true
|
| 23 |
+
},
|
| 24 |
+
"pack_impl": "cpu"
|
| 25 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>"
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 238 |
+
"unk_token": null,
|
| 239 |
+
"_commit_hash": null
|
| 240 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|