metadata
license: apache-2.0
datasets:
- THU-KEG/LongWriter-Zero-RLData
base_model: THU-KEG/LongWriter-Zero-32B
tags:
- reinforcement-learning
- writing
- Long Context
- mlx
- mlx-my-repo
language:
- en
- zh
pipeline_tag: text-generation
library_name: transformers
qurk41/LongWriter-Zero-32B-mlx-4Bit
The Model qurk41/LongWriter-Zero-32B-mlx-4Bit was converted to MLX format from THU-KEG/LongWriter-Zero-32B using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("qurk41/LongWriter-Zero-32B-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)