File size: 3,573 Bytes
29745d3 f7930f4 29745d3 9c63ad9 29745d3 9c63ad9 29745d3 7fd1a15 29745d3 9c63ad9 29745d3 9c63ad9 29745d3 9c63ad9 29745d3 f7930f4 29745d3 2d34c2f 2222759 2d34c2f |
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 81 82 83 84 85 86 87 |
import gradio as gr
import os
from openai import OpenAI
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
# Set your API keys as environment variables or replace os.getenv with your actual keys
DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
# Initialize OpenAI clients
openai_client = OpenAI(api_key=OPENAI_API_KEY)
deepseek_client = OpenAI(api_key=DEEPSEEK_API_KEY, base_url="https://api.deepseek.com")
def generate_response(model_provider, prompt, temperature, top_p, max_tokens, repetition_penalty):
if model_provider == "DeepSeek":
try:
response = deepseek_client.chat.completions.create(
model="deepseek-chat", # or "deepseek-reasoner" for R1 model
messages=[{"role": "user", "content": prompt}],
temperature=temperature,
top_p=top_p,
max_tokens=max_tokens,
presence_penalty=repetition_penalty,
stream=False
)
return response.choices[0].message.content.strip()
except Exception as e:
return f"DeepSeek API Error: {str(e)}"
elif model_provider == "OpenAI":
try:
response = openai_client.chat.completions.create(
model="gpt-3.5-turbo", # or another model of your choice
messages=[{"role": "user", "content": prompt}],
temperature=temperature,
top_p=top_p,
max_tokens=max_tokens,
presence_penalty=repetition_penalty,
stream=False
)
return response.choices[0].message.content.strip()
except Exception as e:
return f"OpenAI API Error: {str(e)}"
else:
return "Invalid model provider selected."
with gr.Blocks() as demo:
gr.Markdown("## 🔍 LLM Chat Interface")
with gr.Row():
model_provider = gr.Dropdown(
choices=["DeepSeek", "OpenAI"],
value="DeepSeek",
label="Select Model Provider"
)
prompt = gr.Textbox(label="Enter your prompt", lines=4, placeholder="Type your message here...")
with gr.Accordion("Advanced Settings", open=False):
temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
top_p = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p")
max_tokens = gr.Slider(32, 2048, value=512, step=32, label="Max New Tokens")
repetition_penalty = gr.Slider(1.0, 2.0, value=1.1, step=0.1, label="Repetition Penalty")
output = gr.Textbox(label="Response")
submit = gr.Button("Generate")
submit.click(
fn=generate_response,
inputs=[prompt, model_provider, temperature, top_p, max_tokens, repetition_penalty],
outputs=output
)
iface = gr.Interface(
fn=generate_response,
inputs=[
gr.Dropdown(choices=["DeepSeek", "OpenAI"], value="DeepSeek", label="Model Provider"),
gr.Textbox(label="Prompt", lines=6, placeholder="Ask something..."),
gr.Slider(minimum=0.1, maximum=1.5, value=0.7, step=0.1, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
gr.Slider(minimum=32, maximum=2048, value=512, step=32, label="Max New Tokens"),
gr.Slider(minimum=1.0, maximum=2.0, value=1.1, step=0.1, label="Repetition Penalty")
],
outputs="text",
title="🧠 DeepSeek LLM Chat with Parameter Tuning",
theme=gr.themes.Soft()
)
# demo.launch()
iface.launch() |