File size: 1,594 Bytes
11c7953
178f86d
 
 
 
11c7953
178f86d
 
 
11c7953
178f86d
 
11c7953
178f86d
 
 
 
11c7953
178f86d
 
 
 
 
 
11c7953
178f86d
11c7953
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
from fastapi import FastAPI
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("cognitivecomputations/Dolphin3.0-Mistral-24B")
model = AutoModelForCausalLM.from_pretrained("cognitivecomputations/Dolphin3.0-Mistral-24B", torch_dtype=torch.float16).cuda()

# FastAPI app
app = FastAPI()

# Request Body
class InputText(BaseModel):
    prompt: str
    max_length: int = 100

@app.post("/generate")
async def generate_text(input_data: InputText):
    inputs = tokenizer(input_data.prompt, return_tensors="pt").to("cuda")
    output = model.generate(**inputs, max_length=input_data.max_length)
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
    return {"response": generated_text}

# Run the server using: uvicorn app:app --host 0.0.0.0 --port 8000



"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()