metadata
quantized_by: bartowski
pipeline_tag: text-generation
license: apache-2.0
base_model: lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bit
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct/blob/main/LICENSE
language:
- en
tags:
- code
- codeqwen
- chat
- qwen
- qwen-coder
- mlx
- mlx-my-repo
library_name: mlx
introvoyz041/Qwen2.5-Coder-14B-Instruct-MLX-4bit-mlx-4Bit
The Model introvoyz041/Qwen2.5-Coder-14B-Instruct-MLX-4bit-mlx-4Bit was converted to MLX format from lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bit using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("introvoyz041/Qwen2.5-Coder-14B-Instruct-MLX-4bit-mlx-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)