--
Browse files
app.py
CHANGED
|
@@ -1,7 +1,145 @@
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
|
| 7 |
-
demo.launch()
|
|
|
|
| 1 |
+
# app.py
|
| 2 |
+
|
| 3 |
import gradio as gr
|
| 4 |
+
import torch
|
| 5 |
+
from unsloth import FastLanguageModel
|
| 6 |
+
import langid
|
| 7 |
+
|
| 8 |
+
# 1. ๋ชจ๋ธ๊ณผ ํ ํฌ๋์ด์ ๋ฅผ ์ ์ญ์ ์ผ๋ก ํ ๋ฒ๋ง ๋ก๋ํฉ๋๋ค.
|
| 9 |
+
# Zero-GPU ํ๊ฒฝ์ ๋ง๊ฒ 4๋นํธ๋ก ๋ชจ๋ธ์ ๋ก๋ํฉ๋๋ค.
|
| 10 |
+
max_seq_length = 2048
|
| 11 |
+
model, tokenizer = FastLanguageModel.from_pretrained(
|
| 12 |
+
model_name="unsloth/DeepSeek-R1-0528-Qwen3-8B",
|
| 13 |
+
max_seq_length=max_seq_length,
|
| 14 |
+
load_in_4bit=True,
|
| 15 |
+
# Zero-GPU(CPU) ํ๊ฒฝ์ด๋ฏ๋ก vLLM ๋นํ์ฑํ
|
| 16 |
+
fast_inference=False,
|
| 17 |
+
# LoRA ์ด๋ํฐ๋ฅผ ๋ก๋ํ๊ธฐ ์ํด ๋ฏธ๋ฆฌ ์ต๋ ๋ญํฌ๋ฅผ ์ง์ ํฉ๋๋ค.
|
| 18 |
+
max_lora_rank=32,
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
# PEFT ๋ชจ๋ธ์ LoRA ๋ชจ๋์ ์ถ๊ฐํฉ๋๋ค.
|
| 22 |
+
# ์ด ๋จ๊ณ๋ ์ถํ model.load_lora()๋ฅผ ์ฌ์ฉํ๊ธฐ ์ํด ํ์ํฉ๋๋ค.
|
| 23 |
+
model = FastLanguageModel.get_peft_model(
|
| 24 |
+
model,
|
| 25 |
+
r=32,
|
| 26 |
+
target_modules=[
|
| 27 |
+
"q_proj", "k_proj", "v_proj", "o_proj",
|
| 28 |
+
"gate_proj", "up_proj", "down_proj",
|
| 29 |
+
],
|
| 30 |
+
lora_alpha=64,
|
| 31 |
+
use_gradient_checkpointing="unsloth",
|
| 32 |
+
random_state=3407,
|
| 33 |
+
)
|
| 34 |
+
|
| 35 |
+
# 2. ์์คํ
ํ๋กฌํํธ ์ ์
|
| 36 |
+
# ๋
ธํธ๋ถ์์ ์ฌ์ฉ๋ ๊ฒ๊ณผ ๋์ผํ ์์คํ
ํ๋กฌํํธ์
๋๋ค.
|
| 37 |
+
system_prompt = (
|
| 38 |
+
"You are given a problem.\n"
|
| 39 |
+
"Think about the problem and provide your working out.\n"
|
| 40 |
+
"You must think in Bahasa Indonesia."
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
# 3. ์ถ๋ก ํจ์ ์ ์
|
| 44 |
+
def generate_response(user_prompt, use_lora):
|
| 45 |
+
"""
|
| 46 |
+
์ฌ์ฉ์ ์
๋ ฅ๊ณผ LoRA ์ฌ์ฉ ์ฌ๋ถ์ ๋ฐ๋ผ ๋ชจ๋ธ ์๋ต์ ์์ฑํฉ๋๋ค.
|
| 47 |
+
"""
|
| 48 |
+
lora_request = None
|
| 49 |
+
if use_lora:
|
| 50 |
+
try:
|
| 51 |
+
# Hugging Face Space์ ํจ๊ป ์
๋ก๋๋ LoRA ์ด๋ํฐ๋ฅผ ๋ก๋ํฉ๋๋ค.
|
| 52 |
+
# ํด๋ ์ด๋ฆ์ ๋
ธํธ๋ถ์์ ์ ์ฅํ 'grpo_lora'์ ์ผ์นํด์ผ ํฉ๋๋ค.
|
| 53 |
+
lora_request = model.load_lora("grpo_lora")
|
| 54 |
+
except Exception as e:
|
| 55 |
+
return f"LoRA ์ด๋ํฐ๋ฅผ ๋ก๋ํ๋ ๋ฐ ์คํจํ์ต๋๋ค: {e}\n'grpo_lora' ํด๋๋ฅผ Space์ ์
๋ก๋ํ๋์ง ํ์ธํ์ธ์.", "์ค๋ฅ"
|
| 56 |
+
|
| 57 |
+
# ์ฑํ
ํ
ํ๋ฆฟ ํ์์ ๋ง๊ฒ ์
๋ ฅ ๋ฉ์์ง๋ฅผ ๊ตฌ์ฑํฉ๋๋ค.
|
| 58 |
+
messages = [
|
| 59 |
+
{"role": "system", "content": system_prompt},
|
| 60 |
+
{"role": "user", "content": user_prompt},
|
| 61 |
+
]
|
| 62 |
+
|
| 63 |
+
# ํ ํฌ๋์ด์ ๋ฅผ ์ฌ์ฉํ์ฌ ์
๋ ฅ ํ
์คํธ๋ฅผ ํฌ๋งทํ
ํฉ๋๋ค.
|
| 64 |
+
input_text = tokenizer.apply_chat_template(
|
| 65 |
+
messages,
|
| 66 |
+
add_generation_prompt=True,
|
| 67 |
+
tokenize=False,
|
| 68 |
+
)
|
| 69 |
+
|
| 70 |
+
inputs = tokenizer(input_text, return_tensors="pt").to("cpu")
|
| 71 |
+
|
| 72 |
+
# ๋ชจ๋ธ์ ์ฌ์ฉํ์ฌ ํ
์คํธ ์์ฑ
|
| 73 |
+
# Unsloth๋ CPU์์๋ ๋น ๋ฅธ ์์ฑ์ ์ง์ํฉ๋๋ค.
|
| 74 |
+
outputs = model.generate(
|
| 75 |
+
**inputs,
|
| 76 |
+
max_new_tokens=512,
|
| 77 |
+
use_cache=True,
|
| 78 |
+
pad_token_id=tokenizer.eos_token_id
|
| 79 |
+
)
|
| 80 |
+
|
| 81 |
+
generated_text = tokenizer.batch_decode(outputs)[0]
|
| 82 |
+
|
| 83 |
+
# ์์ฑ๋ ํ
์คํธ์์ ํ๋กฌํํธ๋ฅผ ์ ์ธํ๊ณ ์์ ์๋ต๋ง ์ถ์ถํฉ๋๋ค.
|
| 84 |
+
response_only = generated_text[len(input_text):]
|
| 85 |
+
|
| 86 |
+
# ์์ฑ๋ ์๋ต์ ์ธ์ด๋ฅผ ๊ฐ์งํฉ๋๋ค.
|
| 87 |
+
lang, score = langid.classify(response_only)
|
| 88 |
+
lang_info = f"๊ฐ์ง๋ ์ธ์ด: {lang} (์ ๋ขฐ๋: {score:.2f})"
|
| 89 |
+
|
| 90 |
+
return response_only, lang_info
|
| 91 |
+
|
| 92 |
|
| 93 |
+
# 4. Gradio ์ธํฐํ์ด์ค ๊ตฌ์ฑ
|
| 94 |
+
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
| 95 |
+
gr.Markdown(
|
| 96 |
+
"""
|
| 97 |
+
# ๐ฎ๐ฉ DeepSeek-R1-Qwen3-8B ๋ชจ๋ธ ์ถ๋ก (GRPO ํ๋)
|
| 98 |
+
์ด ๋ชจ๋ธ์ ์ํ ๋ฌธ์ ์ ๋ํด ์ธ๋๋ค์์์ด๋ก ์ถ๋ก ๊ณผ์ ์ ์ค๋ช
ํ๋๋ก ๋ฏธ์ธ ์กฐ์ ๋์์ต๋๋ค.
|
| 99 |
+
- **'์ธ๋๋ค์์์ด ์ถ๋ก LoRA ์ ์ฉ'** ์ฒดํฌ๋ฐ์ค๋ฅผ ํ์ฑํํ๋ฉด, ํ์ต๋ LoRA ๊ฐ์ค์น๊ฐ ์ ์ฉ๋์ด ์ธ๋๋ค์์์ด๋ก ๋ ๋ต๋ณ์ ์์ฑํ๋๋ก ์ ๋ํฉ๋๋ค.
|
| 100 |
+
- ์ฒดํฌ๋ฐ์ค๋ฅผ ๋นํ์ฑํํ๋ฉด ์๋ณธ ๋ชจ๋ธ์ ์ถ๋ก ๋ฅ๋ ฅ์ ํ์ธํ ์ ์์ต๋๋ค.
|
| 101 |
+
"""
|
| 102 |
+
)
|
| 103 |
+
|
| 104 |
+
with gr.Row():
|
| 105 |
+
with gr.Column(scale=2):
|
| 106 |
+
prompt_input = gr.Textbox(
|
| 107 |
+
label="์ง๋ฌธ ์
๋ ฅ",
|
| 108 |
+
placeholder="์: Solve (x + 2)^2 = 0"
|
| 109 |
+
)
|
| 110 |
+
lora_checkbox = gr.Checkbox(
|
| 111 |
+
label="์ธ๋๋ค์์์ด ์ถ๋ก LoRA ์ ์ฉ",
|
| 112 |
+
value=True
|
| 113 |
+
)
|
| 114 |
+
submit_button = gr.Button("์์ฑํ๊ธฐ", variant="primary")
|
| 115 |
+
|
| 116 |
+
with gr.Column(scale=3):
|
| 117 |
+
output_text = gr.Textbox(
|
| 118 |
+
label="๋ชจ๋ธ ์๋ต",
|
| 119 |
+
interactive=False
|
| 120 |
+
)
|
| 121 |
+
language_info = gr.Textbox(
|
| 122 |
+
label="์ธ์ด ๊ฐ์ง ๊ฒฐ๊ณผ",
|
| 123 |
+
interactive=False
|
| 124 |
+
)
|
| 125 |
+
|
| 126 |
+
submit_button.click(
|
| 127 |
+
fn=generate_response,
|
| 128 |
+
inputs=[prompt_input, lora_checkbox],
|
| 129 |
+
outputs=[output_text, language_info]
|
| 130 |
+
)
|
| 131 |
+
|
| 132 |
+
gr.Examples(
|
| 133 |
+
[
|
| 134 |
+
["Solve (x + 2)^2 = 0", True],
|
| 135 |
+
["What is the square root of 101?", True],
|
| 136 |
+
["In triangle $ABC$, $\\sin \\angle A = \\frac{4}{5}$ and $\\angle A < 90^\\circ$. Let $D$ be a point outside triangle $ABC$ such that $\\angle BAD = \\angle DAC$ and $\\angle BDC = 90^\\circ$. Suppose that $AD = 1$ and that $\\frac{BD}{CD} = \\frac{3}{2}$. If $AB + AC$ can be expressed in the form $\\frac{a\\sqrt{b}}{c}$ where $a, b, c$ are pairwise relatively prime integers, find $a + b + c$.", True]
|
| 137 |
+
],
|
| 138 |
+
inputs=[prompt_input, lora_checkbox],
|
| 139 |
+
outputs=[output_text, language_info],
|
| 140 |
+
fn=generate_response,
|
| 141 |
+
cache_examples=False,
|
| 142 |
+
)
|
| 143 |
|
| 144 |
+
# Gradio ์ฑ ์คํ
|
| 145 |
+
demo.launch()
|