Spaces:
Paused
Paused
File size: 1,776 Bytes
1efd233 cd39699 89ace7e c1fc3a9 68f9e87 1e1efc2 27bcfa0 c1fc3a9 27bcfa0 1efd233 2ccc88d b50be2b 2ccc88d c1fc3a9 028d122 6bf2756 86fbb40 68f9e87 6bf2756 1efd233 c1fc3a9 0d18b6e c1fc3a9 |
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 52 53 54 |
import gradio as gr
import os
import torch, torchvision, einops
import spaces
import subprocess
from transformers import AutoModelForCausalLM
from huggingface_hub import login
# Install required package
subprocess.run(
"pip install flash-attn --no-build-isolation",
env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
shell=True,
)
hf_token = os.getenv("HF_TOKEN")
login(token=hf_token, add_to_git_credential=True)
# Function to get the model summary
@spaces.GPU
def get_model_summary(model_name):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True).to(device)
return str(model)
# Create the Gradio Blocks interface
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
textbox = gr.Textbox(label="Model Name")
examples = gr.Examples(
examples=[
["google/gemma-7b"],
["microsoft/Phi-3-mini-4k-instruct"],
["meta-llama/Meta-Llama-3-8B"],
["mistralai/Mistral-7B-Instruct-v0.3"],
["vikhyatk/moondream2"],
["microsoft/Phi-3-vision-128k-instruct"],
["openbmb/MiniCPM-Llama3-V-2_5"],
["google/paligemma-3b-mix-224"],
["HuggingFaceM4/idefics2-8b-chatty"],
["mistralai/Codestral-22B-v0.1"]
],
inputs=textbox
)
submit_button = gr.Button("Submit")
with gr.Column():
output = gr.Textbox(label="Output", lines=20)
submit_button.click(fn=get_model_summary, inputs=textbox, outputs=output)
# Launch the interface
demo.launch()
|