File size: 980 Bytes
1c1b7ff dcae18f 27546f8 1c1b7ff c2b376f 1c1b7ff c2b376f 1c1b7ff c2b376f 1c1b7ff bf098de 1c1b7ff c2b376f 1c1b7ff |
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 |
from transformers import AutoTokenizer
import transformers
import torch
import streamlit as st
import os
HF_TOKEN = os.environ.get("HF_TOKEN")
prompt = st.text_input('Prompt', 'Hello, How you doing ?')
model = "meta-llama/Llama-2-13b-chat-hf"
#Not Working
#tokenizer = AutoTokenizer.from_pretrained(model)
def load_model(model):
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float32,
device_map="auto",
do_sample=True,
token=HF_TOKEN,
)
return pipeline
def get_llama_response(pipeline,prompt):
sequences = pipeline(
prompt,
top_k=10,
num_return_sequences=1,
max_length=256,
)
print(sequences[0]['generated_text'])
pipeline = AutoTokenizer.from_pretrained(model, token=HF_TOKEN)
#prompt="Can you help me to write rest api endpoints in python ?"
response = get_llama_response(pipeline,prompt)
st.write('Answer: ',response) |