meriamcherif/Llama-2-7b-chat-hf-Quantized

meriamcherif/Meta-Llama-3-8B-quantized

The Model meriamcherif/Meta-Llama-3-8B-quantized was converted to MLX format from NousResearch/Llama-2-7b-chat-hf using mlx-lm version 0.14.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("meriamcherif/Meta-Llama-3-8B-quantized")
response = generate(model, tokenizer, prompt="hello", verbose=True)