license: apache-2.0
language:
- en
- ro
datasets: - nicoboss/medra-medical
tags: - medical-ai
- clinical-reasoning
- summarization
- diagnosis
- medgemma
- fine-tuned
- mlx
- mlx-my-repo
version: DrMedra v1 – MedGemma Edition
author: Dr. Alexandru Lupoi & @nicoboss
base_model: drwlf/DrMedra4B-abliterated
pipeline_tag: text-generation
jc2375/DrMedra4B-abliterated-mlx-fp16
The Model jc2375/DrMedra4B-abliterated-mlx-fp16 was converted to MLX format from drwlf/DrMedra4B-abliterated using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("jc2375/DrMedra4B-abliterated-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)