Spaces:
Sleeping
Sleeping
File size: 2,071 Bytes
56f16a2 96e4b44 724c4ca 56f16a2 504a6c1 fed089e 504a6c1 a857851 56f16a2 1883988 56f16a2 a857851 56f16a2 1883988 56f16a2 1883988 56f16a2 c1b11f0 56f16a2 c1b11f0 56f16a2 c1b11f0 |
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 61 62 63 64 65 66 |
from huggingface_hub import InferenceClient, login
from transformers import AutoTokenizer
from langchain.chat_models import ChatOpenAI
import os, sys, json
import gradio as gr
# access token with permission to access the model and PRO subscription
#HUGGINGFACEHUB_API_TOKEN = os.getenv("HF_ACCESS_READ")
OAI_API_KEY=os.getenv("OPENAI_API_KEY")
login(token=os.environ["HF_ACCESS_READ"])
# tokenizer for generating prompt
print ("Tokenizer")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
# inference client
print ("Inf.Client")
client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")
# generate function
def generate(text):
payload = tokenizer.apply_chat_template([{"role":"user","content":text}],tokenize=False)
res = client.text_generation(
payload,
do_sample=True,
return_full_text=False,
max_new_tokens=2048,
top_p=0.9,
temperature=0.6,
)
print (res)
return res.strip()
# test client
#assert generate("What is 2+2?") == "The answer to 2+2 is 4."
# create evaluator
#assert OAI_API_KEY is not None, "Please set OPENAI_API_KEY environment variable"
evaluation_llm = ChatOpenAI(model="gpt-4")
################################################
#GUI
###############################################
#Beschreibung oben in GUI
################################################
chatbot_stream = gr.Chatbot()
chat_interface_stream = gr.ChatInterface(fn=generate,
title = "ChatGPT vom LI",
theme="soft",
chatbot=chatbot_stream,
retry_btn="🔄 Wiederholen",
undo_btn="↩️ Letztes löschen",
clear_btn="🗑️ Verlauf löschen",
submit_btn = "Abschicken",
)
with gr.Blocks() as demo:
with gr.Tab("Chatbot"):
#chatbot_stream.like(vote, None, None)
chat_interface_stream.queue().launch()
|