Spaces:
Sleeping
Sleeping
File size: 2,800 Bytes
fe2da2c f32132a c00cd01 fe2da2c f32132a fe2da2c f32132a fe2da2c f32132a fe2da2c f32132a |
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 |
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, TextIteratorStreamer
from threading import Thread
import gradio as gr
model = AutoPeftModelForCausalLM.from_pretrained("adlsdztony/Rui-1.5B")
tokenizer = AutoTokenizer.from_pretrained("adlsdztony/Rui-3B")
# from huggingface_hub import InferenceClient
# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# client = InferenceClient("adlsdztony/Rui-3B")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
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})
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([prompt], return_tensors='pt', padding=True, truncation=True)
streamer = TextIteratorStreamer(tokenizer)
generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_p=top_p)
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
generate_text = ''
for new_text in streamer:
output = new_text.replace(prompt, '')
if output:
generate_text += output
yield generate_text
# response = ""
# 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
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="你是小锐，你只会说中文，你会自称为‘锐’，你的工作是每天告诉同学明天的天气和一些最近发生的事情，最后你会跟同学说晚安", 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()
|