Mistral (Mamba) Codestral
Collection
5 items • Updated
How to use mlx-community/Mamba-Codestral-7B-v0.1 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Mamba-Codestral-7B-v0.1 mlx-community/Mamba-Codestral-7B-v0.1
Configuration Parsing Warning:Invalid JSON for config file config.json
The Model mlx-community/Mamba-Codestral-7B-v0.1 was converted to MLX format from mistralai/Mamba-Codestral-7B-v0.1 using mlx-lm version 0.21.0.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Mamba-Codestral-7B-v0.1")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
Quantized
Base model
mistralai/Mamba-Codestral-7B-v0.1