README.md

metadata

base_model: nicoboss/DeepSeek-R1-Distill-Qwen-14B-Uncensored
library_name: peft
tags:
  - generated_from_trainer
  - mlx
  - mlx-my-repo
license: mit
datasets:
  - Guilherme34/uncensor
model-index:
  - name: DeepSeek-R1-Distill-Qwen-14B-Uncensored
    results: []

isv2lf/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Q6-mlx

The Model isv2lf/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Q6-mlx was converted to MLX format from nicoboss/DeepSeek-R1-Distill-Qwen-14B-Uncensored using mlx-lm version 0.20.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("isv2lf/DeepSeek-R1-Distill-Qwen-14B-Uncensored-Q6-mlx")

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)