Instructions to use Intel/Ovis-Image-7B-int4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Intel/Ovis-Image-7B-int4-AutoRound with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Intel/Ovis-Image-7B-int4-AutoRound", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| { | |
| "_class_name": "OvisImageTransformer2DModel", | |
| "_diffusers_version": "0.36.0.dev0", | |
| "_name_or_path": "/mnt/disk4/lvl/Ovis-Image-7B/transformer", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "in_channels": 64, | |
| "joint_attention_dim": 2048, | |
| "num_attention_heads": 24, | |
| "num_layers": 6, | |
| "num_single_layers": 27, | |
| "out_channels": null, | |
| "patch_size": 1, | |
| "quantization_config": { | |
| "autoround_version": "0.13.0", | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "transformer_blocks,single_transformer_blocks", | |
| "data_type": "int", | |
| "group_size": 128, | |
| "nsamples": 64, | |
| "packing_format": "auto_round:auto_gptq", | |
| "quant_method": "auto-round", | |
| "sym": true | |
| } | |
| } | |