Spaces:
Runtime error
Runtime error
File size: 6,807 Bytes
23ba7d5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
from typing import List
import argparse
import gradio as gr
import torch
from threading import Thread
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
TextIteratorStreamer
)
import warnings
warnings.filterwarnings('ignore', category=UserWarning, message='TypedStorage is deprecated')
parser = argparse.ArgumentParser()
parser.add_argument("--model_path", type=str, default="")
parser.add_argument("--torch_dtype", type=str, default="bfloat16")
parser.add_argument("--server_name", type=str, default="127.0.0.1")
parser.add_argument("--server_port", type=int, default=7860)
args = parser.parse_args()
# init model torch dtype
torch_dtype = args.torch_dtype
if torch_dtype =="" or torch_dtype == "bfloat16":
torch_dtype = torch.bfloat16
elif torch_dtype == "float32":
torch_dtype = torch.float32
else:
raise ValueError(f"Invalid torch dtype: {torch_dtype}")
# init model and tokenizer
path = args.model_path
tokenizer = AutoTokenizer.from_pretrained(path)
model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch_dtype, device_map="auto", trust_remote_code=True)
# init gradio demo host and port
server_name=args.server_name
server_port=args.server_port
def hf_gen(dialog: List, top_p: float, temperature: float, max_dec_len: int):
"""generate model output with huggingface api
Args:
query (str): actual model input.
top_p (float): only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
temperature (float): Strictly positive float value used to modulate the logits distribution.
max_dec_len (int): The maximum numbers of tokens to generate.
Yields:
str: real-time generation results of hf model
"""
inputs = tokenizer.apply_chat_template(dialog, tokenize=False, add_generation_prompt=False)
enc = tokenizer(inputs, return_tensors="pt").to("cuda")
streamer = TextIteratorStreamer(tokenizer)
generation_kwargs = dict(
enc,
do_sample=True,
top_p=top_p,
temperature=temperature,
max_new_tokens=max_dec_len,
pad_token_id=tokenizer.eos_token_id,
streamer=streamer,
)
thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()
answer = ""
for new_text in streamer:
answer += new_text
yield answer[4 + len(inputs):]
def generate(chat_history: List, query: str, top_p: float, temperature: float, max_dec_len: int):
"""generate after hitting "submit" button
Args:
chat_history (List): [[q_1, a_1], [q_2, a_2], ..., [q_n, a_n]]. list that stores all QA records
query (str): query of current round
top_p (float): only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
temperature (float): strictly positive float value used to modulate the logits distribution.
max_dec_len (int): The maximum numbers of tokens to generate.
Yields:
List: [[q_1, a_1], [q_2, a_2], ..., [q_n, a_n], [q_n+1, a_n+1]]. chat_history + QA of current round.
"""
assert query != "", "Input must not be empty!!!"
# apply chat template
model_input = []
for q, a in chat_history:
model_input.append({"role": "user", "content": q})
model_input.append({"role": "assistant", "content": a})
model_input.append({"role": "user", "content": query})
# yield model generation
chat_history.append([query, ""])
for answer in hf_gen(model_input, top_p, temperature, max_dec_len):
chat_history[-1][1] = answer.strip("</s>")
yield gr.update(value=""), chat_history
def regenerate(chat_history: List, top_p: float, temperature: float, max_dec_len: int):
"""re-generate the answer of last round's query
Args:
chat_history (List): [[q_1, a_1], [q_2, a_2], ..., [q_n, a_n]]. list that stores all QA records
top_p (float): only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
temperature (float): strictly positive float value used to modulate the logits distribution.
max_dec_len (int): The maximum numbers of tokens to generate.
Yields:
List: [[q_1, a_1], [q_2, a_2], ..., [q_n, a_n]]. chat_history
"""
assert len(chat_history) >= 1, "History is empty. Nothing to regenerate!!"
# apply chat template
model_input = []
for q, a in chat_history[:-1]:
model_input.append({"role": "user", "content": q})
model_input.append({"role": "assistant", "content": a})
model_input.append({"role": "user", "content": chat_history[-1][0]})
# yield model generation
for answer in hf_gen(model_input, top_p, temperature, max_dec_len):
chat_history[-1][1] = answer.strip("</s>")
yield gr.update(value=""), chat_history
def clear_history():
"""clear all chat history
Returns:
List: empty chat history
"""
return []
def reverse_last_round(chat_history):
"""reverse last round QA and keep the chat history before
Args:
chat_history (List): [[q_1, a_1], [q_2, a_2], ..., [q_n, a_n]]. list that stores all QA records
Returns:
List: [[q_1, a_1], [q_2, a_2], ..., [q_n-1, a_n-1]]. chat_history without last round.
"""
assert len(chat_history) >= 1, "History is empty. Nothing to reverse!!"
return chat_history[:-1]
# launch gradio demo
with gr.Blocks(theme="soft") as demo:
gr.Markdown("""# MiniCPM Gradio Demo""")
with gr.Row():
with gr.Column(scale=1):
top_p = gr.Slider(0, 1, value=0.8, step=0.1, label="top_p")
temperature = gr.Slider(0.1, 2.0, value=0.8, step=0.1, label="temperature")
max_dec_len = gr.Slider(1, 1024, value=1024, step=1, label="max_dec_len")
with gr.Column(scale=5):
chatbot = gr.Chatbot(bubble_full_width=False, height=400)
user_input = gr.Textbox(label="User", placeholder="Input your query here!", lines=8)
with gr.Row():
submit = gr.Button("Submit")
clear = gr.Button("Clear")
regen = gr.Button("Regenerate")
reverse = gr.Button("Reverse")
submit.click(generate, inputs=[chatbot, user_input, top_p, temperature, max_dec_len], outputs=[user_input, chatbot])
regen.click(regenerate, inputs=[chatbot, top_p, temperature, max_dec_len], outputs=[user_input, chatbot])
clear.click(clear_history, inputs=[], outputs=[chatbot])
reverse.click(reverse_last_round, inputs=[chatbot], outputs=[chatbot])
demo.queue()
demo.launch(server_name=server_name, server_port=server_port, show_error=True, share=True)
|