Instructions to use microsoft/Magma-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/Magma-8B with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("microsoft/Magma-8B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from microsoft/Magma-8B: direct link, hf CLI and curl.
- Browser
- Download file 434 Bytes
-
https://huggingface.co/microsoft/Magma-8B/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://microsoft/Magma-8B/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/microsoft/Magma-8B/resolve/main/special_tokens_map.json
434 Bytes
| { | |
| "bos_token": { | |
| "content": "<|begin_of_text|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|eot_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |