metadata
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- chat
- instruct
- small-model
- 135m
- quark
- mlx
base_model: ThingAI/Quark-135m
usermma/Quark-135m-mlx-5bit
The Model usermma/Quark-135m-mlx-5bit was converted to MLX format from ThingAI/Quark-135m using mlx-lm version 0.31.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("usermma/Quark-135m-mlx-5bit")
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)