Instructions to use apocryphx/gemma-4-E2B-it-q4-apml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use apocryphx/gemma-4-E2B-it-q4-apml with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download apocryphx/gemma-4-E2B-it-q4-apml --local-dir gemma-4-E2B-it-q4-apml
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from apocryphx/gemma-4-E2B-it-q4-apml: direct link, hf CLI and curl.
- Browser
- Download file 208 Bytes
-
https://huggingface.co/apocryphx/gemma-4-E2B-it-q4-apml/resolve/e5dca0144fca4037de908b9b9ffa77f3248814fa/generation_config.json
- Command line
-
hf download hf://apocryphx/gemma-4-E2B-it-q4-apml@e5dca0144fca4037de908b9b9ffa77f3248814fa/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/apocryphx/gemma-4-E2B-it-q4-apml/resolve/e5dca0144fca4037de908b9b9ffa77f3248814fa/generation_config.json
208 Bytes
| { | |
| "bos_token_id": 2, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 1, | |
| 106, | |
| 50 | |
| ], | |
| "pad_token_id": 0, | |
| "temperature": 1.0, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "transformers_version": "5.5.0.dev0" | |
| } | |