File size: 1,071 Bytes
2b6b154 d24a963 1b3204d d24a963 2b6b154 09e1b8b 1b3204d 2b6b154 09e1b8b 1b3204d 09e1b8b |
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 |
import gradio as gr
import spaces
import torch
import transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "meta-llama/Meta-Llama-3-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16,device_map="auto")
@spaces.GPU
def yes_man(message, history):
input_ids = tokenizer(message, return_tensors="pt").input_ids.to(model.device)
output = model.generate(input_ids, max_length=512, num_return_sequences=1)
detailed_prompt = tokenizer.decode(output[0], skip_special_tokens=True)
return detailed_prompt
gr.ChatInterface(
yes_man,
chatbot=gr.Chatbot(height=300),
textbox=gr.Textbox(placeholder="Enter message here", container=False, scale=7),
title="LLAMA 3 8B Chat",
description="Ask Yes Man any question",
theme="soft",
examples=["Hello", "Am I cool?", "Are tomatoes vegetables?"],
cache_examples=True,
retry_btn=None,
undo_btn="Delete Previous",
clear_btn="Clear",
).launch() |