File size: 1,203 Bytes
9bc80c6 b782268 9bc80c6 |
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 |
import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model = AutoModelForCausalLM.from_pretrained("checkpoint/",trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("checkpoint/", trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
def inference(prompt, count):
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200)
result = pipe(f"### Human: {prompt}",max_new_tokens=count)
out_text = result[0]['generated_text']
return out_text
title = "TSAI S21 Assignment: Adaptive QLoRA training on open assist oasst1 dataset, using microsoft/phi2 model"
description = "A simple Gradio interface that accepts a context and generates GPT like text "
examples = [["What is a large language model?","200"],
["Explain about monopsony","200"]
]
demo = gr.Interface(
inference,
inputs = [gr.Textbox(placeholder="Enter a prompt"), gr.Textbox(placeholder="Enter number of characters you want to generate")],
outputs = [gr.Textbox(label="Chat GPT like text")],
title = title,
description = description,
examples = examples
)
demo.launch() |