Instructions to use failspy/InternVL-Chat-V1-5-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use failspy/InternVL-Chat-V1-5-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="failspy/InternVL-Chat-V1-5-4bit", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("failspy/InternVL-Chat-V1-5-4bit", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "</box>": 92552, | |
| "</img>": 92545, | |
| "</quad>": 92548, | |
| "</ref>": 92550, | |
| "<IMG_CONTEXT>": 92546, | |
| "<box>": 92551, | |
| "<img>": 92544, | |
| "<quad>": 92547, | |
| "<ref>": 92549 | |
| } | |