Instructions to use bodhicitta/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bodhicitta/sam3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="bodhicitta/sam3")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("bodhicitta/sam3") model = AutoModel.from_pretrained("bodhicitta/sam3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from bodhicitta/sam3: direct link, hf CLI and curl.
- Browser
- Download file 588 Bytes
-
https://huggingface.co/bodhicitta/sam3/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://bodhicitta/sam3/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/bodhicitta/sam3/resolve/main/special_tokens_map.json
588 Bytes
| { | |
| "bos_token": { | |
| "content": "<|startoftext|>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |