metadata
language:
- en
license: llama3.2
library_name: transformers
pipeline_tag: text-generation
tags:
- llama-3.2
- oncology
- clinical-trials
- distillation
- information-extraction
- mlx
- mlx-my-repo
base_model: ksg-dfci/OncoReasoning-3B
kenlkehl/OncoReasoning-3B-mlx-8Bit
The Model kenlkehl/OncoReasoning-3B-mlx-8Bit was converted to MLX format from ksg-dfci/OncoReasoning-3B using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("kenlkehl/OncoReasoning-3B-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)