Spaces:
Sleeping
Sleeping
File size: 2,706 Bytes
4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 4559b07 ec2ec98 |
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
from huggingface_hub import InferenceClient
# Define available models
MODELS = {
"Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
"GPT-2": "gpt2",
"GPT-2 Medium": "gpt2-medium",
"DistilGPT-2": "distilgpt2",
"German GPT-2": "german-nlp-group/german-gpt2",
"German Wechsel GPT-2": "benjamin/gpt2-wechsel-german",
"T5 Base": "t5-base",
"T5 Large": "t5-large"
}
def create_inference_client(model_name):
"""Create an InferenceClient for the selected model."""
try:
return InferenceClient(model_name)
except Exception as e:
print(f"Error creating client for {model_name}: {e}")
return None
def respond(
message,
history: list[tuple[str, str]],
system_message,
model_name,
max_tokens,
temperature,
top_p,
):
"""Generate response using selected model."""
# Create client for selected model
client = create_inference_client(MODELS[model_name])
if not client:
return "Error: Could not create model client."
# Prepare chat history
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
# Generate response
try:
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content or ""
response += token
yield response
except Exception as e:
yield f"Error during generation: {e}"
def create_chat_interface():
"""Create Gradio ChatInterface with model selection."""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Dropdown(list(MODELS.keys()), value="Zephyr 7B Beta", label="Select Model"),
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)",
),
]
)
return demo
if __name__ == "__main__":
chat_interface = create_chat_interface()
chat_interface.launch(share=True) |