File size: 2,362 Bytes
8caa0ea 45123a0 8caa0ea 93f1a1e 8caa0ea cc6666c 8caa0ea fe6d4e0 8caa0ea 93f1a1e 8caa0ea 93f1a1e 8caa0ea |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient(
base_url="https://huggingface.co/api/integrations/dgx/v1"
# api_key="..." # Uncomment and use your actual API key here if required
)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
model,
):
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})
response = ""
for message in client.chat_completion(
messages,
model=model, #"meta-llama/Meta-Llama-3.1-8B-Instruct",
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
if token:
response += token
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
# List of model IDs
model_options = [
"meta-llama/Meta-Llama-3.1-8B-Instruct",
"meta-llama/Meta-Llama-3.1-70B-Instruct",
"meta-llama/Meta-Llama-3.1-405B-Instruct-FP8",
"meta-llama/Meta-Llama-3-8B-Instruct",
"meta-llama/Meta-Llama-3-70B-Instruct",
"mistralai/Mistral-7B-Instruct-v0.3",
"mistralai/Mixtral-8x7B-Instruct-v0.1",
"mistralai/Mixtral-8x22B-Instruct-v0.1",
]
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", 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)"),
gr.Dropdown(choices=model_options, value=model_options[0], label="Model"), # Dropdown for model selection
],
)
if __name__ == "__main__":
demo.launch() |