Spaces:
Runtime error
Runtime error
File size: 2,243 Bytes
cef78d8 9a6eb7d 6f6480f fd50bcf cf7efe0 9a6eb7d fd50bcf 9a6eb7d fd50bcf 6f6480f fd50bcf 6f6480f fd50bcf 3d441a2 fd50bcf 6f6480f 3d441a2 9a5e8aa 9a6eb7d fd50bcf | 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 55 56 57 58 59 60 | import os
from dotenv import load_dotenv, find_dotenv
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch
# Load environment variables
_ = load_dotenv(find_dotenv())
hf_api_key = os.environ['HF_API_KEY']
model_name = "tiiuae/falcon-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
text_gen_pipeline = pipeline(
"text-generation",
model=model_name,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
)
class Client:
def __init__(self, pipeline):
self.pipeline = pipeline
def generate_text(self, prompt, max_new_tokens, temperature):
sequences = self.pipeline(
prompt,
max_length=max_new_tokens,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
return sequences[0]['generated_text']
client = Client(text_gen_pipeline)
def format_chat_prompt(message, chat_history, instruction):
prompt = f"System:{instruction}"
for turn in chat_history:
user_message, bot_message = turn
prompt = f"{prompt}\nUser: {user_message}\nAssistant: {bot_message}"
prompt = f"{prompt}\nUser: {message}\nAssistant:"
return prompt
def respond(message, chat_history, instruction, temperature=0.7):
prompt = format_chat_prompt(message, chat_history, instruction)
chat_history = chat_history + [[message, ""]]
output_text = client.generate_text(prompt, max_new_tokens=1024, temperature=temperature)
last_turn = list(chat_history.pop(-1))
last_turn[-1] += output_text
chat_history = chat_history + [last_turn]
return "", chat_history
iface = gr.Interface(fn=respond, inputs=[gr.Textbox(label="Prompt"), gr.Chatbot(label="Chat History", height=240), gr.Textbox(label="System message", lines=2, value="A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers."), gr.Slider(label="temperature", minimum=0.1, maximum=1, value=0.7, step=0.1)], outputs=[gr.Textbox(label="Prompt"), gr.Chatbot(label="Chat History", height=240)])
if __name__ == "__main__":
iface.launch()
|