license: apache-2.0
base_model: huizimao/gpt-oss-20b-uncensored-mxfp4
library_name: mlx
tags:
- mlx
pipeline_tag: text-generation
huizimao-gpt-oss-20b-uncensored-mxfp4-q4-hi-mlx
This model contains config and template fixes by Unsloth
This model huizimao-gpt-oss-20b-uncensored-mxfp4-q4-hi-mlx was
converted to MLX format from huizimao/gpt-oss-20b-uncensored-mxfp4
using mlx-lm version 0.26.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("huizimao-gpt-oss-20b-uncensored-mxfp4-q4-hi-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)