| license: apache-2.0 | |
| base_model: AIDC-AI/Ovis2-2B | |
| tags: | |
| - quantized | |
| - awq | |
| - vision-language-model | |
| - vlm | |
| # AIDC-AI__Ovis2-2B__awq_w4 | |
| This is a **AWQ** (4-bit) quantized version of [AIDC-AI/Ovis2-2B](https://huggingface.co/AIDC-AI/Ovis2-2B). | |
| ## Quantization Details | |
| - **Method**: AWQ | |
| - **Bits**: 4 | |
| - **Base model**: AIDC-AI/Ovis2-2B | |
| - **Group size**: 128 | |
| ## Usage | |
| ```python | |
| from transformers import AutoProcessor, AutoModelForImageTextToText | |
| import torch | |
| model = AutoModelForImageTextToText.from_pretrained( | |
| "{REPO_ID}", | |
| torch_dtype=torch.float16, | |
| device_map="auto", | |
| trust_remote_code=True, | |
| ) | |
| processor = AutoProcessor.from_pretrained("{REPO_ID}", trust_remote_code=True) | |
| ``` | |
| Replace `{REPO_ID}` with the repo ID of this model. | |
| ## Original Model | |
| See [AIDC-AI/Ovis2-2B](https://huggingface.co/AIDC-AI/Ovis2-2B) for the original FP16 model. | |