MLX
Safetensors
English
llama
Llama-3
instruct
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
function calling
json mode
axolotl
merges
Instructions to use typealias/Hermes-2-Theta-Llama-3-8B-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use typealias/Hermes-2-Theta-Llama-3-8B-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Hermes-2-Theta-Llama-3-8B-mlx-4bit typealias/Hermes-2-Theta-Llama-3-8B-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Ctrl+K