Image-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
quantized
fp8
8bit
vision-language-model
qwen3-vl
compressed-tensors
vllm
smoothquant
Instructions to use JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic") model = AutoModelForMultimodalLM.from_pretrained("JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic: direct link, hf CLI and curl.
- Browser
- Download file 1.86 kB
-
https://huggingface.co/JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic/resolve/main/processor_config.json
- Command line
-
hf download hf://JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/JEILDLWLRMA/Qwen3-VL-4B-Instruct-FP8-Dynamic/resolve/main/processor_config.json
1.86 kB
| { | |
| "image_processor": { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "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 | |
| }, | |
| "processor_class": "Qwen3VLProcessor", | |
| "video_processor": { | |
| "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_pad": null, | |
| "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, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "temporal_patch_size": 2, | |
| "video_metadata": null, | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } | |
| } | |