Spaces:
Running
Running
File size: 2,780 Bytes
76ce008 |
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 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
from huggingface_hub import InferenceClient
import gradio as gr
import random
client = InferenceClient("google/gemma-2b-it")
def format_prompt(message, history):
prompt = ""
if history:
for user_prompt, bot_response in history:
prompt += f"<start_of_turn>user{user_prompt}<end_of_turn>"
prompt += f"<start_of_turn>model{bot_response}"
prompt += f"<start_of_turn>user{message}<end_of_turn><start_of_turn>model"
return prompt
def generate(prompt, history, temperature=0.7, max_new_tokens=1024, top_p=0.90, repetition_penalty=0.9):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
if not history:
history = []
rand_seed = random.randint(1, 1111111111111111)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=rand_seed,
)
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
history.append((prompt, output))
return output
mychatbot = gr.Chatbot(
avatar_images=["./user.png", "./botgm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
additional_inputs=[
gr.Slider(
label="Temperature",
value=0.7,
minimum=0.0,
maximum=1.0,
step=0.01,
interactive=True,
info="Higher values generate more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=6400,
minimum=0,
maximum=8000,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p",
value=0.90,
minimum=0.0,
maximum=1,
step=0.01,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.0,
minimum=0.1,
maximum=2.0,
step=0.1,
interactive=True,
info="Penalize repeated tokens",
)
]
iface = gr.ChatInterface(fn=generate,
chatbot=mychatbot,
additional_inputs=additional_inputs,
retry_btn=None,
undo_btn=None
)
with gr.Blocks() as demo:
gr.HTML("<center><h1>Tomoniai's Chat with Google's Gemma</h1></center>")
iface.render()
demo.queue().launch(show_api=False) |