Image-to-Text
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
text-to-image
image-to-image
edit
reasoning
reward
Instructions to use TIGER-Lab/RationalRewards-8B-T2I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/RationalRewards-8B-T2I 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="TIGER-Lab/RationalRewards-8B-T2I")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("TIGER-Lab/RationalRewards-8B-T2I") model = AutoModelForImageTextToText.from_pretrained("TIGER-Lab/RationalRewards-8B-T2I") - Notebooks
- Google Colab
- Kaggle
| { | |
| "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": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |