File size: 744 Bytes
f343423 5ac4d70 f343423 5ac4d70 f343423 5ac4d70 f343423 5ac4d70 f343423 5ac4d70 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch
model_id = "aaditya/Llama3-OpenBioLLM-8B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
torch_dtype=torch.float16
)
chat_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
def chatbot(message, history=[]):
prompt = f"[INST] {message} [/INST]"
response = chat_pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)[0]['generated_text']
return response.replace(prompt, "").strip()
gr.ChatInterface(fn=chatbot, title="🩺 OpenBioLLM Chatbot", description="Ask me anything biomedical!").launch()
|