Spaces:
Runtime error
Runtime error
File size: 950 Bytes
6ca34cf 0d9b453 6ca34cf 0d9b453 899a5f6 6ca34cf d733851 899a5f6 6ca34cf b4a0c25 6ca34cf f0b7b32 0d9b453 6ca34cf 0866bfe f0b7b32 0866bfe dedd577 f0b7b32 dedd577 b09cd28 0866bfe |
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 |
import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
torch.random.manual_seed(0)
proc_model = AutoModelForCausalLM.from_pretrained(
"microsoft/Phi-3-mini-4k-instruct",
trust_remote_code=True,
)
proc_model.to("cpu")
proc_model.eval()
proc_tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
proc_pipe = pipeline(
"text-generation",
model=proc_model,
tokenizer=proc_tokenizer,
)
generation_args = {
"max_new_tokens": 500,
"return_full_text": False,
"temperature": 0.0,
"do_sample": False,
}
def generate_response(inputs):
output = proc_pipe(inputs, **generation_args)
return output[0]['generated_text']
# Create a Gradio interface
iface = gr.Interface(
fn=generate_response,
inputs=[gr.Textbox(lines=5, placeholder="Enter your prompt here...")]
outputs=gr.Textbox()
)
# Launch the interface
iface.launch() |