Spaces:
Sleeping
Sleeping
File size: 2,060 Bytes
23c43ca 4a49528 7503b0d 23c43ca fc9ba7d 23c43ca 4a49528 23c43ca 7503b0d 4a49528 23c43ca 4a49528 23c43ca 4a49528 23c43ca 4a49528 23c43ca 4a49528 23c43ca 4a49528 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# Initialize the InferenceClient with the model name
# client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
client = InferenceClient("meta-llama/Llama-3.2-11B-Vision-Instruct")
def respond(
message,
history,
system_message,
max_tokens,
temperature,
top_p,
):
# Create a list of messages with the system message and user input
messages = [{"role": "system", "content": system_message}, {"role": "user", "content": message}]
# Calculate the total token count
total_token_count = sum(len(m["content"].split()) for m in messages) + max_tokens
# Truncate the input message if necessary
if total_token_count > 4096:
excess_tokens = total_token_count - 4096
for i in range(len(messages) - 1, -1, -1):
if len(messages[i]["content"].split()) > excess_tokens:
messages[i]["content"] = " ".join(messages[i]["content"].split()[:-excess_tokens])
break
else:
excess_tokens -= len(messages[i]["content"].split())
messages[i]["content"] = ""
# Get the response from the model
response = client.chat_completion(
messages,
max_tokens=max_tokens,
stream=False,
temperature=temperature,
top_p=top_p,
)
# Return the response
return response.choices[0].message.content
# Create a ChatInterface with the respond function and additional inputs
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)",
),
],
)
if __name__ == "__main__":
demo.launch() |