Spaces:
Running
Running
File size: 785 Bytes
d170fb3 75254e1 55c4154 d170fb3 d5d2fa8 d170fb3 fe5503a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
model_id = "tiiuae/falcon-rw-1b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
def chat_with_expert(message, history):
prompt = f"<s>[INST] You are an expert assistant. Answer with clarity and depth.\n{message} [/INST]"
response = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)[0]['generated_text']
answer = response.split('[/INST]')[-1].strip()
history.append((message, answer))
return history, history
chatbot = gr.ChatInterface(fn=chat_with_expert, title="Expert Chat Assistant")
chatbot.launch()
|