llava-med-v1.5-mistral-7b-hf

This repository contains a drop-in, Hugging Face–compatible checkpoint converted from
https://huggingface.co/microsoft/llava-med-v1.5-mistral-7b.
You can load it with the exact same code you use for the original model—no extra conversion steps required.

---

Quick Start

from transformers import LlavaForConditionalGeneration, AutoProcessor
import torch

model_path = "chaoyinshe/llava-med-v1.5-mistral-7b-hf"

model = LlavaForConditionalGeneration.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",   # requires FA2
    device_map="auto"                          # multi-GPU ready
)

processor = AutoProcessor.from_pretrained(model_path)

# Example inference
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"type": "text", "text": "What is the main finding in this chest X-ray?"}
        ]
    }
]

prompt = processor.tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

inputs = processor(
    images=[image], text=prompt, return_tensors="pt"
).to(model.device, torch.bfloat16)

with torch.inference_mode():
    out = model.generate(**inputs, max_new_tokens=256)

print(processor.decode(out[0], skip_special_tokens=True))