Spaces:
Running
Running
File size: 1,796 Bytes
c615bd3 f858622 c615bd3 15b3be2 f858622 15b3be2 cfbc2ff f858622 c615bd3 ebb3fac c615bd3 ebb3fac c615bd3 15b3be2 c615bd3 15b3be2 c615bd3 cfbc2ff c615bd3 cfbc2ff c615bd3 cfbc2ff |
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
from llama_cpp import Llama
# Initialize the InferenceClient
client = InferenceClient()
llm = Llama.from_pretrained(
repo_id="bartowski/Reasoning-Llama-1b-v0.1-GGUF",
filename="Reasoning-Llama-1b-v0.1-f16.gguf",
)
# Fixed system message
SYSTEM_MESSAGE = "You are a friendly, conversational, helpful, and informative chatbot. Your responses should be quirky and fun to read, including the use of appropriate emojis in answers where necessary."
def respond(
message,
history: list[tuple[str, str]],
max_tokens,
temperature,
top_p,
):
# Use fixed system message
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 = ""
# Use the client to get the chat completion
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']
response += token
yield response
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Maximum Response Length"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Creativity"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Neuron Firing Rate",
),
],
)
if __name__ == "__main__":
demo.launch()
|