File size: 1,516 Bytes
d4a9c54 1871f0d d4a9c54 1871f0d 20ea8ef 1871f0d d4a9c54 023ef9c d4a9c54 023ef9c d4a9c54 4ae60a7 023ef9c fec4095 bf86fa8 |
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 os
import gradio as gr
from huggingface_hub import login
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from transformers import pipeline
# Fetch API token from environment variable
api_token = os.getenv("Llama_Token")
# Authenticate with Hugging Face
login(api_token)
# Load LLaMA 3.2 model and tokenizer with the API token
model_name = "meta-llama/Llama-3.2-1B"
tokenizer = AutoTokenizer.from_pretrained(model_name, token=api_token)
model = AutoModelForCausalLM.from_pretrained(model_name, token=api_token)
pipe = pipeline("text-generation", model=model_name, torch_dtype=torch.bfloat16, device_map="auto")
pipe("How are you doing?")
# # Define the inference function
# def generate_text(prompt, max_length, temperature):
# inputs = tokenizer(prompt, return_tensors="pt")
# output = model.generate(inputs['input_ids'], max_length=max_length, temperature=temperature)
# return tokenizer.decode(output[0], skip_special_tokens=True)
# # Create the Gradio interface
# iface = gr.Interface(
# fn=generate_text,
# inputs=[
# gr.Textbox(label="Enter your prompt", placeholder="Start typing..."),
# gr.Slider(minimum=50, maximum=200, label="Max Length", value=100),
# gr.Slider(minimum=0.1, maximum=1.0, label="Temperature", value=0.7),
# ],
# outputs="text",
# title="LLaMA 3.2 Text Generator",
# description="Enter a prompt to generate text using the LLaMA 3.2 model.",
# )
# # Launch the Gradio app
# iface.launch()
|