license: other
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags: - qwen3
- text-generation
- littlelearner
- unbounded
- instruct
- reinforcement-learning
- mlx
- mlx-my-repo
base_model: littlelearner/unfiltered-5b-grpo-math-expert
jeweled/unfiltered-5b-grpo-math-expert-mlx-8Bit
The Model jeweled/unfiltered-5b-grpo-math-expert-mlx-8Bit was converted to MLX format from littlelearner/unfiltered-5b-grpo-math-expert using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("jeweled/unfiltered-5b-grpo-math-expert-mlx-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)