Instructions to use immanuelpeter/Inkling-2-Small-Vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use immanuelpeter/Inkling-2-Small-Vision with timm:
import timm model = timm.create_model("hf-hub:immanuelpeter/Inkling-2-Small-Vision", pretrained=True) - PerceptionEncoder
How to use immanuelpeter/Inkling-2-Small-Vision with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("immanuelpeter/Inkling-2-Small-Vision", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download config.json from immanuelpeter/Inkling-2-Small-Vision: direct link, hf CLI and curl.
- Browser
- Download file 431 Bytes
-
https://huggingface.co/immanuelpeter/Inkling-2-Small-Vision/resolve/main/config.json
- Command line
-
hf download hf://immanuelpeter/Inkling-2-Small-Vision/config.json
-
curl -L -o config.json https://huggingface.co/immanuelpeter/Inkling-2-Small-Vision/resolve/main/config.json
431 Bytes
| { | |
| "temporal_patch_size": 2, | |
| "native_patch_size": 20, | |
| "adapter_merge_size": 2, | |
| "projection_hidden_dim": 4096, | |
| "projector_bias": false, | |
| "hidden_size": 1024, | |
| "num_hidden_layers": 23, | |
| "num_attention_heads": 16, | |
| "mlp_ratio": 4.0, | |
| "posemb_grid_size": 32, | |
| "layer_norm_eps": 1e-05, | |
| "text_hidden_size": 4608, | |
| "image_size": 640, | |
| "timm_architecture": "vit_pe_lang_large_patch14_448", | |
| "torch_dtype": "bfloat16" | |
| } | |