ipetrukha/Nxcode-CQ-7B-orpo-4bit
The Model ipetrukha/Nxcode-CQ-7B-orpo-4bit was converted to MLX format from NTQAI/Nxcode-CQ-7B-orpo using mlx-lm version 0.14.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ipetrukha/Nxcode-CQ-7B-orpo-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 29
Inference API (serverless) does not yet support mlx models for this pipeline type.