license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterate/blob/main/LICENSE
language:
- en
base_model: huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated
pipeline_tag: text-generation
library_name: transformers
tags: - code
- codeqwen
- chat
- qwen
- qwen-coder
- abliterated
- uncensored
- mlx
- mlx-my-repo
KYUNGYONG/Qwen2.5-Coder-14B-Instruct-abliterated-4bit
The Model KYUNGYONG/Qwen2.5-Coder-14B-Instruct-abliterated-4bit was converted to MLX format from huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated using mlx-lm version 0.21.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("KYUNGYONG/Qwen2.5-Coder-14B-Instruct-abliterated-4bit")
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)