metadata
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- vllm
- mlx
- gpt-oss-safeguard
- openai
- gpt-oss
- gpt
- oss
base_model: openai/gpt-oss-safeguard-20b
base_model_relation: quantized
SiddhJagani/gpt-oss-safeguard-20b-mlx-3Bit
The Model SiddhJagani/gpt-oss-safeguard-20b-mlx-3Bit was converted to MLX format from openai/gpt-oss-safeguard-20b using mlx-lm version 0.28.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("SiddhJagani/gpt-oss-safeguard-20b-mlx-Q3")
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
)
# Force our custom assistant marker
prompt = force_generation_prompt(prompt)
response = generate(model, tokenizer, prompt=prompt, verbose=True)