metadata
license: apache-2.0
language:
- en
- zh
base_model: YOYO-AI/ZYH-LLM-Qwen2.5-14B-V5
pipeline_tag: text-generation
tags:
- merge
- mlx
- mlx-my-repo
m-i/ZYH-LLM-Qwen2.5-14B-V5-mlx-8Bit
The Model m-i/ZYH-LLM-Qwen2.5-14B-V5-mlx-8Bit was converted to MLX format from YOYO-AI/ZYH-LLM-Qwen2.5-14B-V5 using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("m-i/ZYH-LLM-Qwen2.5-14B-V5-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)