File size: 1,308 Bytes
9c9ed59 8341989 9c9ed59 8341989 9c9ed59 8341989 9c9ed59 ca677a9 9c9ed59 e95e8e1 8341989 1afe06d e95e8e1 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient(
"mistralai/Mixtral-8x7B-Instruct-v0.1"
)
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt, history, system_prompt, top_p=0.95, repetition_penalty=1.0,
):
top_p = float(top_p)
generate_kwargs = dict(
temperature=0.9, # Fixed temperature
max_new_tokens=2560, # Updated max_new_tokens value
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
output = ""
for response in stream:
output += response.token.text
yield output
return output
gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
title="Nova v2",
concurrency_limit=20,
).launch(show_api=False) |