Spaces:
Sleeping
Sleeping
File size: 1,333 Bytes
9d164d3 1bb02a4 9d164d3 1bb02a4 9d164d3 |
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 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import tempfile
import os
# Create the offload folder
offload_dir = './offload'
os.makedirs(offload_dir, exist_ok=True)
model = AutoModelForCausalLM.from_pretrained(
"tiiuae/falcon-7b-instruct",
torch_dtype=torch.bfloat16,
device_map="auto",
low_cpu_mem_usage=True,
offload_folder=offload_dir
)
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-7b-instruct")
def generate_text(input_text):
input_ids = tokenizer.encode(input_text, return_tensors="pt")
attention_mask = torch.ones(input_ids.shape)
output = model.generate(
input_ids,
attention_mask=attention_mask,
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(output_text)
# Remove Prompt Echo from Generated Text
cleaned_output_text = output_text.replace(input_text, "")
return cleaned_output_text
text_generation_interface = gr.Interface(
fn=generate_text,
inputs=[
gr.inputs.Textbox(label="Input Text"),
],
outputs=gr.inputs.Textbox(label="Generated Text"),
title="Falcon-7B Instruct",
).launch()
|