teknium/OpenHermes-2.5
Viewer • Updated • 1M • 20.1k • 834
How to use TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-196c8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir OpenHermes-2.5-Mistral-7B-MLX-196c8 TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-196c8
The Model TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-196c8 was converted to MLX format from teknium/OpenHermes-2.5-Mistral-7B using mlx-lm version 0.20.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("TheBlueObserver/OpenHermes-2.5-Mistral-7B-MLX-196c8")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
4-bit
Base model
mistralai/Mistral-7B-v0.1