File size: 1,390 Bytes
073e04b 86e8c59 073e04b 16db460 86e8c59 16db460 073e04b 16db460 6fa8b69 073e04b 16db460 6fa8b69 073e04b 16db460 6fa8b69 073e04b 86e8c59 073e04b 86e8c59 073e04b 16db460 073e04b |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# 🔹 Initialize Hugging Face Inference Client
client = InferenceClient(model="one1cat/FineTunes_LLM_CFR_49")
def respond(message, history, system_message, max_tokens, temperature, top_p):
"""
Generates responses using the fine-tuned CFR 49 model hosted on Hugging Face.
"""
prompt = f"{system_message}\n\nUser: {message}\n\nAssistant:"
response = ""
try:
# 🔥 Use raw API request instead of `text_generation()`
result = client.post(
json={"inputs": prompt, "parameters": {
"max_new_tokens": max_tokens,
"temperature": temperature,
"top_p": top_p
}},
)
response = result.text
yield response
except Exception as e:
yield f"Error: {str(e)}"
# 🔹 Gradio Chat Interface
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a CFR 49 regulatory compliance assistant.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
],
)
if __name__ == "__main__":
demo.launch()
|