metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- vllm
- mlx
- mlx-my-repo
base_model: unsloth/gpt-oss-20b
mrtoots/unsloth-gpt-oss-20b-mlx-fp16
The Model mrtoots/unsloth-gpt-oss-20b-mlx-fp16 was converted to MLX format from unsloth/gpt-oss-20b using mlx-lm version 0.26.4.
Toots' Note:
This model was converted and quantized utilizing unsloth's version of gpt-oss-20b.
Please follow and support unsloth's work if you like it!
🦛 If you want a free consulting session, fill out this form to get in touch! 🤗
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mrtoots/gpt-oss-20b-mlx-fp16")
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)