File size: 1,723 Bytes
301b6fb 90a8ffa bb9d04d 90a8ffa bb9d04d 301b6fb 90a8ffa 78f2093 90a8ffa 78f2093 90a8ffa 6bcba58 90a8ffa 6bcba58 90a8ffa |
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 |
import os
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import gradio as gr
def greet(name, req: gr.Request):
return f"{req.headers=}"
iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()
# Disable hf_transfer
os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "false"
app = FastAPI()
# Load your fine-tuned model and tokenizer
model_name = "OnlyCheeini/greesychat-turbo"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Check if a GPU is available, otherwise use CPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32).to(device)
class OpenAIRequest(BaseModel):
model: str
prompt: str
max_tokens: int = 64
temperature: float = 0.7
top_p: float = 0.9
class OpenAIResponse(BaseModel):
choices: list
@app.post("/v1/completions", response_model=OpenAIResponse)
async def generate_text(request: OpenAIRequest):
if request.model != model_name:
raise HTTPException(status_code=400, detail="Model not found")
inputs = tokenizer(request.prompt, return_tensors="pt").to(device)
outputs = model.generate(
**inputs,
max_length=inputs['input_ids'].shape[1] + request.max_tokens,
temperature=request.temperature,
top_p=request.top_p,
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return OpenAIResponse(choices=[{"text": generated_text}])
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=8000) |