Spaces:
Runtime error
Runtime error
File size: 1,919 Bytes
8f0412a d6219de 1192448 7d0535a 1192448 8f0412a 039ebfd 7d0535a 8f0412a d6219de 8f0412a d6219de 8f0412a d6219de 8f0412a d6219de 1192448 8f0412a 7d0535a 8f0412a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
from fastapi import FastAPI, UploadFile, Form
from fastapi.responses import JSONResponse
from transformers import AutoProcessor, AutoModelForVision2Seq
import torch
from PIL import Image
import io
app = FastAPI(title="Aloe Vision Backend")
print("🚀 Loading model, please wait...")
model_id = "HPAI-BSC/Aloe-Vision-7B-AR"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForVision2Seq.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
print("✅ Model loaded!")
@app.post("/analyze")
async def analyze(file: UploadFile, prompt: str = Form("Describe the image")):
"""Receive an image + prompt, return model output."""
try:
image_bytes = await file.read()
image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
messages = [
{
"role": "user",
"content": [
{"type": "image", "image": image},
{"type": "text", "text": prompt}
]
}
]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs = processor.process_vision_info(messages)
inputs = processor(
text=[text],
**image_inputs,
return_tensors="pt"
).to(model.device)
generated = model.generate(
**inputs,
max_new_tokens=256,
do_sample=False,
eos_token_id=processor.tokenizer.eos_token_id,
)
output_text = processor.batch_decode(generated, skip_special_tokens=True)[0]
return {"result": output_text}
except Exception as e:
return JSONResponse(content={"error": str(e)}, status_code=500)
@app.get("/")
def root():
return {"status": "ok", "message": "Aloe Vision Backend running!"}
|