README.md

metadata

library_name: transformers
license: apache-2.0
license_link: >-
  https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2/blob/main/LICENSE
language:
  - en
pipeline_tag: text-generation
base_model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
tags:
  - chat
  - abliterated
  - uncensored
  - mlx
  - mlx-my-repo

Fmuaddib/Qwen2.5-14B-Instruct-abliterated-v2-mlx-8Bit

The Model Fmuaddib/Qwen2.5-14B-Instruct-abliterated-v2-mlx-8Bit was converted to MLX format from huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/Qwen2.5-14B-Instruct-abliterated-v2-mlx-8Bit")

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)