Instructions to use failspy/InternVL-Chat-V1-5-quantable with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use failspy/InternVL-Chat-V1-5-quantable with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="failspy/InternVL-Chat-V1-5-quantable", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("failspy/InternVL-Chat-V1-5-quantable", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ datasets:
|
|
| 10 |
pipeline_tag: visual-question-answering
|
| 11 |
---
|
| 12 |
|
| 13 |
-
Comes with two
|
| 14 |
|
| 15 |
# Original Model Card for InternVL-Chat-V1.5
|
| 16 |
<p align="center">
|
|
|
|
| 10 |
pipeline_tag: visual-question-answering
|
| 11 |
---
|
| 12 |
|
| 13 |
+
[Comes with two line fixes for multi-GPUs](https://github.com/OpenGVLab/InternVL/issues/96)
|
| 14 |
|
| 15 |
# Original Model Card for InternVL-Chat-V1.5
|
| 16 |
<p align="center">
|