metadata
language:
- en
- zh
library_name: transformers
tags:
- Long Context
- chatglm
- llama
- mlx
- mlx-my-repo
datasets:
- THUDM/LongWriter-6k
license: llama3.1
base_model: zai-org/LongWriter-llama3.1-8b
mlx-community/LongWriter-llama3.1-8b-8bit
The Model mlx-community/LongWriter-llama3.1-8b-8bit was converted to MLX format from zai-org/LongWriter-llama3.1-8b using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/LongWriter-llama3.1-8b-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)