Spaces:
Runtime error
Runtime error
File size: 1,993 Bytes
e80c50c a7a5fa9 e80c50c b169b98 e80c50c 545b577 a7a5fa9 e80c50c 545b577 e80c50c 5d30ce0 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
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, temperature=0.5, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0,
):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_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
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values generate more diverse outputs",
),
gr.Slider(
label="max_new_tokens",
value=512,
minimum=1,
maximum=2048,
step=1,
interactive=True,
info="Higher values allows for longer answers",
)
]
bbchatbot = gr.Chatbot(
avatar_images=["./user.png", "./bot.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
demo = gr.ChatInterface(fn=generate,
chatbot=bbchatbot,
title="🫐TheBlueberry-AI's Chat with Mistral 7B v0.2🪄",
additional_inputs=additional_inputs
)
demo.queue().launch() |