metadata
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- mlx
- mlx-my-repo
base_model: TheDrummer/Llama-3SOME-8B-v2
DreamsOfControl/Llama-3SOME-8B-v2-mlx-2Bit
The Model DreamsOfControl/Llama-3SOME-8B-v2-mlx-2Bit was converted to MLX format from TheDrummer/Llama-3SOME-8B-v2 using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("DreamsOfControl/Llama-3SOME-8B-v2-mlx-2Bit")
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)