Visual Question Answering
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
multimodal
text-generation-inference
Instructions to use TIGER-Lab/VL-Rethinker-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/VL-Rethinker-72B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="TIGER-Lab/VL-Rethinker-72B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TIGER-Lab/VL-Rethinker-72B") model = AutoModelForMultimodalLM.from_pretrained("TIGER-Lab/VL-Rethinker-72B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from TIGER-Lab/VL-Rethinker-72B: direct link, hf CLI and curl.
- Browser
- Download file 268 Bytes
-
https://huggingface.co/TIGER-Lab/VL-Rethinker-72B/resolve/main/generation_config.json
- Command line
-
hf download hf://TIGER-Lab/VL-Rethinker-72B/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/TIGER-Lab/VL-Rethinker-72B/resolve/main/generation_config.json
268 Bytes
| { | |
| "attn_implementation": "flash_attention_2", | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "top_k": 1, | |
| "top_p": 0.001, | |
| "transformers_version": "4.49.0" | |
| } | |