Spaces:
Sleeping
Sleeping
File size: 2,385 Bytes
3afe7b3 |
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 |
import torch
from transformers import AutoTokenizer
from model import TransformerModel # Replace with your model class
import gradio as gr
# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/cosmo2-tokenizer")
# Load the model
def load_model(checkpoint_path):
# Initialize the model (replace with your model's configuration)
model = TransformerModel(
vocab_size=49152,
hidden_size=576,
num_hidden_layers=30,
num_attention_heads=9,
intermediate_size=1536,
num_key_value_heads=3,
max_position_embeddings=2048,
rms_norm_eps=1e-5,
hidden_act="silu",
tie_word_embeddings=True,
pad_token_id=tokenizer.pad_token_id,
)
# Load the checkpoint
checkpoint = torch.load(checkpoint_path, map_location="cpu")
model.load_state_dict(checkpoint["model_state_dict"])
model.eval()
return model
# Load the model
model = load_model("checkpoint_5050_quantized.pt")
# Function to generate text
def generate_text(prompt, max_length=50, temperature=1.0, top_k=50):
# Encode the prompt
input_ids = tokenizer.encode(prompt, return_tensors="pt")
# Generate text
with torch.no_grad():
output_ids = model.generate(
input_ids,
max_length=max_length,
temperature=temperature,
top_k=top_k,
do_sample=True,
)
# Decode the generated text
generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
return generated_text
# Gradio Interface
def gradio_generate_text(prompt, max_length, temperature, top_k):
return generate_text(prompt, max_length, temperature, top_k)
# Create the Gradio app
interface = gr.Interface(
fn=gradio_generate_text,
inputs=[
gr.Textbox(label="Prompt", placeholder="Enter your prompt here..."),
gr.Slider(minimum=10, maximum=200, value=50, label="Max Length"),
gr.Slider(minimum=0.1, maximum=2.0, value=1.0, label="Temperature"),
gr.Slider(minimum=1, maximum=100, value=50, label="Top-k Sampling"),
],
outputs=gr.Textbox(label="Generated Text"),
title="Text Generation with SMOL-LM2",
description="Generate text using the SMOL-LM2 model.",
)
# Launch the app
interface.launch() |