Spaces:
Running
Running
File size: 2,363 Bytes
0efa81e 1e819e6 ed53c37 0efa81e 1e819e6 8f95bbc 0efa81e f71f3be 9dad4e7 0efa81e 9dad4e7 0efa81e 9dad4e7 0efa81e 9dad4e7 0efa81e f71f3be 0efa81e fccd59a |
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 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import gradio as gr
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
# Load the model and tokenizer from Hugging Face
model_name = "facebook/opt-125m"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Initialize vLLM with CPU configuration
vllm_model = LLM(model=model_name, tensor_parallel_size=1, device="cpu")
def generate_response(prompt, max_tokens, temperature, top_p):
# Tokenize the prompt
inputs = tokenizer(prompt, return_tensors="pt")["input_ids"].tolist()[0]
# Define sampling parameters
sampling_params = SamplingParams(
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
)
# Generate text using vLLM
output = vllm_model.generate(inputs, sampling_params)
# Decode the generated tokens to text
generated_text = tokenizer.decode(output[0].outputs[0].token_ids, skip_special_tokens=True)
return generated_text
# Gradio UI
with gr.Blocks() as demo:
gr.Markdown("# 🚀 Hugging Face Integration with vLLM (CPU)")
gr.Markdown("Generate text using the vLLM integration with Hugging Face models on CPU.")
with gr.Row():
with gr.Column():
prompt_input = gr.Textbox(
label="Prompt",
placeholder="Enter your prompt here...",
lines=3,
)
max_tokens = gr.Slider(
label="Max Tokens",
minimum=10,
maximum=500,
value=100,
step=10,
)
temperature = gr.Slider(
label="Temperature",
minimum=0.1,
maximum=1.0,
value=0.7,
step=0.1,
)
top_p = gr.Slider(
label="Top P",
minimum=0.1,
maximum=1.0,
value=0.9,
step=0.1,
)
submit_button = gr.Button("Generate")
with gr.Column():
output_text = gr.Textbox(
label="Generated Text",
lines=10,
interactive=False,
)
submit_button.click(
generate_response,
inputs=[prompt_input, max_tokens, temperature, top_p],
outputs=output_text,
)
# Launch the app
demo.launch()
|