File size: 1,049 Bytes
6ff2499 674e436 6ff2499 e4dfb4a 674e436 ec9d3dc 57c7d18 3e61735 674e436 322a100 674e436 322a100 674e436 |
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
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# Load your model from Hugging Face Transformers
model_name = "deepseek-ai/DeepSeek-V2-Lite"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16).cpu()
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id
# Define a function to use the model
def math_inference(input_text):
inputs = tokenizer(input_text, return_tensors="pt")
output = model.generate(**inputs)
response = tokenizer.decode(output[0], skip_special_tokens=True)
return response
# Create a Gradio interface
iface = gr.Interface(
fn=math_inference,
inputs=gr.Textbox(prompt="Input math question"),
outputs=gr.Textbox(prompt="Math answer"),
layout="vertical",
title="Math Solver"
)
# Launch the Gradio interface
iface.launch()
|