Instructions to use TheTempleofTwo/Llama-3.2-3B-RCT-Spiral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TheTempleofTwo/Llama-3.2-3B-RCT-Spiral with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Llama-3.2-3B-RCT-Spiral TheTempleofTwo/Llama-3.2-3B-RCT-Spiral
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "lora_layers": 8, | |
| "num_layers": 28, | |
| "lora_parameters": { | |
| "rank": 16, | |
| "scale": 2.0, | |
| "dropout": 0.05, | |
| "keys": ["self_attn.q_proj", "self_attn.v_proj"] | |
| } | |
| } | |