Update README.md
Browse files
README.md
CHANGED
|
@@ -1,172 +1,172 @@
|
|
| 1 |
-
---
|
| 2 |
-
language:
|
| 3 |
-
- ko
|
| 4 |
-
license: mit
|
| 5 |
-
tags:
|
| 6 |
-
- finance
|
| 7 |
-
- extractive-summarization
|
| 8 |
-
- sentence-extraction
|
| 9 |
-
- role-classification
|
| 10 |
-
- korean
|
| 11 |
-
- roberta
|
| 12 |
-
pipeline_tag: text-classification
|
| 13 |
-
base_model: klue/roberta-base
|
| 14 |
-
metrics:
|
| 15 |
-
- f1
|
| 16 |
-
- accuracy
|
| 17 |
-
---
|
| 18 |
-
|
| 19 |
-
# LQ-FSE-base: Korean Financial Sentence Extractor
|
| 20 |
-
|
| 21 |
-
๊ธ์ต ๋ฆฌํฌํธ, ๊ธ์ต ๊ด๋ จ ๋ด์ค์์ ๋ํ๋ฌธ์ฅ์ ์ถ์ถํ๊ณ ์ญํ (outlook, event, financial, risk)์ ๋ถ๋ฅํ๋ ๋ชจ๋ธ์
๋๋ค.
|
| 22 |
-
|
| 23 |
-
## Model Description
|
| 24 |
-
|
| 25 |
-
- **Base Model**: klue/roberta-base
|
| 26 |
-
- **Architecture**: Sentence Encoder (RoBERTa) + Inter-sentence Transformer (2 layers) + Dual Classifiers
|
| 27 |
-
- **Task**: Extractive Summarization + Role Classification (Multi-task)
|
| 28 |
-
- **Language**: Korean
|
| 29 |
-
- **Domain**: Financial Reports (์ฆ๊ถ ๋ฆฌํฌํธ), Financial News (๊ธ์ต ๋ด์ค)
|
| 30 |
-
|
| 31 |
-
### Input Constraints
|
| 32 |
-
|
| 33 |
-
| Parameter | Value | Description |
|
| 34 |
-
|-----------|-------|-------------|
|
| 35 |
-
| Max sentence length | 128 tokens | ๋ฌธ์ฅ๋น ์ต๋ ํ ํฐ ์ (์ด๊ณผ ์ truncation) |
|
| 36 |
-
| Max sentences per document | 30 | ๋ฌธ์๋น ์ต๋ ๋ฌธ์ฅ ์ (์ด๊ณผ ์ ์ 30๊ฐ๋ง ์ฌ์ฉ) |
|
| 37 |
-
| Input format | Plain text | ๋ฌธ์ฅ ๋ถํธ(`.!?`) ๊ธฐ์ค์ผ๋ก ์๋ ๋ถ๋ฆฌ |
|
| 38 |
-
|
| 39 |
-
- **์
๋ ฅ**: ํ๊ตญ์ด ๊ธ์ต ํ
์คํธ (์ฆ๊ถ ๋ฆฌํฌํธ, ๊ธ์ต ๋ด์ค ๋ฑ)
|
| 40 |
-
- **์ถ๋ ฅ**: ๊ฐ ๋ฌธ์ฅ๋ณ ๋ํ๋ฌธ์ฅ ์ ์ (0~1) + ์ญํ ๋ถ๋ฅ (outlook/event/financial/risk)
|
| 41 |
-
|
| 42 |
-
### Performance
|
| 43 |
-
|
| 44 |
-
| Metric | Score |
|
| 45 |
-
|--------|-------|
|
| 46 |
-
| Extraction F1 | 0.705 |
|
| 47 |
-
| Role Accuracy | 0.851 |
|
| 48 |
-
|
| 49 |
-
### Role Labels
|
| 50 |
-
|
| 51 |
-
| Label | Description |
|
| 52 |
-
|-------|-------------|
|
| 53 |
-
| `outlook` | ์ ๋ง/์์ธก ๋ฌธ์ฅ |
|
| 54 |
-
| `event` | ์ด๋ฒคํธ/์ฌ๊ฑด ๋ฌธ์ฅ |
|
| 55 |
-
| `financial` | ์ฌ๋ฌด/์ค์ ๋ฌธ์ฅ |
|
| 56 |
-
| `risk` | ๋ฆฌ์คํฌ ์์ธ ๋ฌธ์ฅ |
|
| 57 |
-
|
| 58 |
-
## Usage
|
| 59 |
-
|
| 60 |
-
```python
|
| 61 |
-
import re
|
| 62 |
-
import torch
|
| 63 |
-
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
| 64 |
-
|
| 65 |
-
repo_id = "LangQuant/LQ-FSE-base"
|
| 66 |
-
|
| 67 |
-
# ๋ชจ๋ธ ๋ก๋
|
| 68 |
-
config = AutoConfig.from_pretrained(repo_id, trust_remote_code=True)
|
| 69 |
-
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
|
| 70 |
-
tokenizer = AutoTokenizer.from_pretrained(repo_id)
|
| 71 |
-
model.eval()
|
| 72 |
-
|
| 73 |
-
# ์
๋ ฅ ํ
์คํธ
|
| 74 |
-
text = (
|
| 75 |
-
"์ผ์ฑ์ ์์ 2024๋
4๋ถ๊ธฐ ์ค์ ์ด ์์ฅ ์์์ ์ํํ๋ค. "
|
| 76 |
-
"๋ฉ๋ชจ๋ฆฌ ๋ฐ๋์ฒด ๊ฐ๊ฒฉ ์์น์ผ๋ก ์์
์ด์ต์ด ์ ๋ถ๊ธฐ ๋๋น 30% ์ฆ๊ฐํ๋ค. "
|
| 77 |
-
"HBM3E ์์ฐ์ด ๋ณธ๊ฒฉํ๋๋ฉด์ AI ๋ฐ๋์ฒด ์์ฅ ์ ์ ์จ์ด ํ๋๋ ์ ๋ง์ด๋ค."
|
| 78 |
-
)
|
| 79 |
-
|
| 80 |
-
# ๋ฌธ์ฅ ๋ถ๋ฆฌ ๋ฐ ํ ํฐํ
|
| 81 |
-
sentences = [s.strip() for s in re.split(r'(?<=[.!?])\s+', text.strip()) if s.strip()]
|
| 82 |
-
max_len, max_sent = config.max_length, config.max_sentences
|
| 83 |
-
|
| 84 |
-
padded = sentences[:max_sent]
|
| 85 |
-
num_real = len(padded)
|
| 86 |
-
while len(padded) < max_sent:
|
| 87 |
-
padded.append("")
|
| 88 |
-
|
| 89 |
-
ids_list, mask_list = [], []
|
| 90 |
-
for s in padded:
|
| 91 |
-
if s:
|
| 92 |
-
enc = tokenizer(s, max_length=max_len, padding="max_length", truncation=True, return_tensors="pt")
|
| 93 |
-
else:
|
| 94 |
-
enc = {"input_ids": torch.zeros(1, max_len, dtype=torch.long),
|
| 95 |
-
"attention_mask": torch.zeros(1, max_len, dtype=torch.long)}
|
| 96 |
-
ids_list.append(enc["input_ids"])
|
| 97 |
-
mask_list.append(enc["attention_mask"])
|
| 98 |
-
|
| 99 |
-
input_ids = torch.cat(ids_list).unsqueeze(0)
|
| 100 |
-
attention_mask = torch.cat(mask_list).unsqueeze(0)
|
| 101 |
-
doc_mask = torch.zeros(1, max_sent)
|
| 102 |
-
doc_mask[0, :num_real] = 1
|
| 103 |
-
|
| 104 |
-
# ์ถ๋ก
|
| 105 |
-
with torch.no_grad():
|
| 106 |
-
scores, role_logits = model(input_ids, attention_mask, doc_mask)
|
| 107 |
-
|
| 108 |
-
role_labels = config.role_labels
|
| 109 |
-
for i, sent in enumerate(sentences):
|
| 110 |
-
score = scores[0, i].item()
|
| 111 |
-
role = role_labels[role_logits[0, i].argmax().item()]
|
| 112 |
-
marker = "*" if score >= 0.5 else " "
|
| 113 |
-
print(f" {marker} [{score:.4f}] [{role:10s}] {sent}")
|
| 114 |
-
```
|
| 115 |
-
|
| 116 |
-
## Model Architecture
|
| 117 |
-
|
| 118 |
-
```
|
| 119 |
-
Input Sentences
|
| 120 |
-
โ
|
| 121 |
-
[klue/roberta-base] โ [CLS] embeddings per sentence
|
| 122 |
-
โ
|
| 123 |
-
[Inter-sentence Transformer] (2 layers, 8 heads)
|
| 124 |
-
โ
|
| 125 |
-
โโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโ
|
| 126 |
-
โ Binary Classifierโ Role Classifier โ
|
| 127 |
-
โ (representative?)โ (outlook/event/ โ
|
| 128 |
-
โ โ financial/risk) โ
|
| 129 |
-
โโโโโโโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโโโโโโโโ
|
| 130 |
-
```
|
| 131 |
-
|
| 132 |
-
## Training
|
| 133 |
-
|
| 134 |
-
- Optimizer: AdamW (lr=2e-5, weight_decay=0.01)
|
| 135 |
-
- Scheduler: Linear warmup (10%)
|
| 136 |
-
- Loss: BCE (extraction) + CrossEntropy (role), role_weight=0.5
|
| 137 |
-
- Max sentence length: 128 tokens
|
| 138 |
-
- Max sentences per document: 30
|
| 139 |
-
|
| 140 |
-
## Files
|
| 141 |
-
|
| 142 |
-
- `model.py`: Model definition (DocumentEncoderConfig, DocumentEncoderForExtractiveSummarization)
|
| 143 |
-
- `config.json`: Model configuration
|
| 144 |
-
- `model.safetensors`: Model weights
|
| 145 |
-
- `inference_example.py`: Inference helper with usage example
|
| 146 |
-
- `convert_checkpoint.py`: Script to convert original .pt checkpoint
|
| 147 |
-
|
| 148 |
-
## Disclaimer (๋ฉด์ฑ
์กฐํญ)
|
| 149 |
-
|
| 150 |
-
- ๋ณธ ๋ชจ๋ธ์ **์ฐ๊ตฌ ๋ฐ ์ ๋ณด ์ ๊ณต ๋ชฉ์ **์ผ๋ก๋ง ์ ๊ณต๋ฉ๋๋ค.
|
| 151 |
-
- ๋ณธ ๋ชจ๋ธ์ ์ถ๋ ฅ์ **ํฌ์ ์กฐ์ธ, ๊ธ
|
| 152 |
-
- ๋ชจ๋ธ์ ์์ธก ๊ฒฐ๊ณผ๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ํ ํฌ์ ํ๋จ์ ๋ํด LangQuant ๋ฐ ๊ฐ๋ฐ์๋ **์ด๋ ํ ๋ฒ์ ์ฑ
์๋ ์ง์ง ์์ต๋๋ค.**
|
| 153 |
-
- ๋ชจ๋ธ์ ์ ํ์ฑ, ์์ ์ฑ, ์ ์์ฑ์ ๋ํด ๋ณด์ฆํ์ง ์์ผ๋ฉฐ, ์ค์ ํฌ์ ์์ฌ๊ฒฐ์ ์ ๋ฐ๋์ ์ ๋ฌธ๊ฐ์ ์กฐ์ธ์ ๊ตฌํ์๊ธฐ ๋ฐ๋๋๋ค.
|
| 154 |
-
- ๊ธ์ต ์์ฅ์ ๋ณธ์ง์ ์ผ๋ก ๋ถํ์คํ๋ฉฐ, ๊ณผ๊ฑฐ ๋ฐ์ดํฐ๋ก ํ์ต๋ ๋ชจ๋ธ์ด ๋ฏธ๋ ์ฑ๊ณผ๋ฅผ ๋ณด์ฅํ์ง ์์ต๋๋ค.
|
| 155 |
-
|
| 156 |
-
## Usage Restrictions (์ฌ์ฉ ์ ํ)
|
| 157 |
-
|
| 158 |
-
- **๊ธ์ง ์ฌํญ:**
|
| 159 |
-
- ๋ณธ ๋ชจ๋ธ์ ์ด์ฉํ ์์ธ ์กฐ์ข
, ํ์ ์ ๋ณด ์์ฑ ๋ฑ ๋ถ๋ฒ์ ๋ชฉ์ ์ ์ฌ์ฉ
|
| 160 |
-
- ์๋ํ๋ ํฌ์ ๋งค๋งค ์์คํ
์ ๋จ๋
์์ฌ๊ฒฐ์ ์๋จ์ผ๋ก ์ฌ์ฉ
|
| 161 |
-
- ๋ชจ๋ธ ์ถ๋ ฅ์ ์ ๋ฌธ ๊ธ์ต ์๋ฌธ์ธ ๊ฒ์ฒ๋ผ ์ 3์์๊ฒ ์ ๊ณตํ๋ ํ์
|
| 162 |
-
- **ํ์ฉ ์ฌํญ:**
|
| 163 |
-
- ํ์ ์ฐ๊ตฌ ๋ฐ ๊ต์ก ๋ชฉ์ ์ ์ฌ์ฉ
|
| 164 |
-
- ๊ธ์ต ํ
์คํธ ๋ถ์ ํ์ดํ๋ผ์ธ์ ๋ณด์กฐ ๋๊ตฌ๋ก ํ์ฉ
|
| 165 |
-
- ์ฌ๋ด ๋ฆฌ์์น/๋ถ์ ์
๋ฌด์ ์ฐธ๊ณ ์๋ฃ๋ก ํ์ฉ
|
| 166 |
-
- ์์
์ ์ฌ์ฉ ์ LangQuant์ ์ฌ์ ๋ฌธ์๋ฅผ ๊ถ์ฅํฉ๋๋ค.
|
| 167 |
-
|
| 168 |
-
## Contributors
|
| 169 |
-
|
| 170 |
-
- **[Taegyeong Lee](https://www.linkedin.com/in/taegyeong-lee/)** (taegyeong.leaf@gmail.com)
|
| 171 |
-
- **[Dong Young Kim](https://www.linkedin.com/in/dykim04/)** (dong-kim@student.42kl.edu.my) โ Ecole 42
|
| 172 |
-
- **[Seunghyun Hwang](https://www.linkedin.com/in/seung-hyun-hwang-53700124a/)** (hsh1030@g.skku.edu) โ DSSAL
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- finance
|
| 7 |
+
- extractive-summarization
|
| 8 |
+
- sentence-extraction
|
| 9 |
+
- role-classification
|
| 10 |
+
- korean
|
| 11 |
+
- roberta
|
| 12 |
+
pipeline_tag: text-classification
|
| 13 |
+
base_model: klue/roberta-base
|
| 14 |
+
metrics:
|
| 15 |
+
- f1
|
| 16 |
+
- accuracy
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# LQ-FSE-base: Korean Financial Sentence Extractor
|
| 20 |
+
|
| 21 |
+
LangQuant(๋ญํํธ)์์ ๊ณต๊ฐํ ๊ธ์ต ๋ฆฌํฌํธ, ๊ธ์ต ๊ด๋ จ ๋ด์ค์์ ๋ํ๋ฌธ์ฅ์ ์ถ์ถํ๊ณ ์ญํ (outlook, event, financial, risk)์ ๋ถ๋ฅํ๋ ๋ชจ๋ธ์
๋๋ค.
|
| 22 |
+
|
| 23 |
+
## Model Description
|
| 24 |
+
|
| 25 |
+
- **Base Model**: klue/roberta-base
|
| 26 |
+
- **Architecture**: Sentence Encoder (RoBERTa) + Inter-sentence Transformer (2 layers) + Dual Classifiers
|
| 27 |
+
- **Task**: Extractive Summarization + Role Classification (Multi-task)
|
| 28 |
+
- **Language**: Korean
|
| 29 |
+
- **Domain**: Financial Reports (์ฆ๊ถ ๋ฆฌํฌํธ), Financial News (๊ธ์ต ๋ด์ค)
|
| 30 |
+
|
| 31 |
+
### Input Constraints
|
| 32 |
+
|
| 33 |
+
| Parameter | Value | Description |
|
| 34 |
+
|-----------|-------|-------------|
|
| 35 |
+
| Max sentence length | 128 tokens | ๋ฌธ์ฅ๋น ์ต๋ ํ ํฐ ์ (์ด๊ณผ ์ truncation) |
|
| 36 |
+
| Max sentences per document | 30 | ๋ฌธ์๋น ์ต๋ ๋ฌธ์ฅ ์ (์ด๊ณผ ์ ์ 30๊ฐ๋ง ์ฌ์ฉ) |
|
| 37 |
+
| Input format | Plain text | ๋ฌธ์ฅ ๋ถํธ(`.!?`) ๊ธฐ์ค์ผ๋ก ์๋ ๋ถ๋ฆฌ |
|
| 38 |
+
|
| 39 |
+
- **์
๋ ฅ**: ํ๊ตญ์ด ๊ธ์ต ํ
์คํธ (์ฆ๊ถ ๋ฆฌํฌํธ, ๊ธ์ต ๋ด์ค ๋ฑ)
|
| 40 |
+
- **์ถ๋ ฅ**: ๊ฐ ๋ฌธ์ฅ๋ณ ๋ํ๋ฌธ์ฅ ์ ์ (0~1) + ์ญํ ๋ถ๋ฅ (outlook/event/financial/risk)
|
| 41 |
+
|
| 42 |
+
### Performance
|
| 43 |
+
|
| 44 |
+
| Metric | Score |
|
| 45 |
+
|--------|-------|
|
| 46 |
+
| Extraction F1 | 0.705 |
|
| 47 |
+
| Role Accuracy | 0.851 |
|
| 48 |
+
|
| 49 |
+
### Role Labels
|
| 50 |
+
|
| 51 |
+
| Label | Description |
|
| 52 |
+
|-------|-------------|
|
| 53 |
+
| `outlook` | ์ ๋ง/์์ธก ๋ฌธ์ฅ |
|
| 54 |
+
| `event` | ์ด๋ฒคํธ/์ฌ๊ฑด ๋ฌธ์ฅ |
|
| 55 |
+
| `financial` | ์ฌ๋ฌด/์ค์ ๋ฌธ์ฅ |
|
| 56 |
+
| `risk` | ๋ฆฌ์คํฌ ์์ธ ๋ฌธ์ฅ |
|
| 57 |
+
|
| 58 |
+
## Usage
|
| 59 |
+
|
| 60 |
+
```python
|
| 61 |
+
import re
|
| 62 |
+
import torch
|
| 63 |
+
from transformers import AutoConfig, AutoModel, AutoTokenizer
|
| 64 |
+
|
| 65 |
+
repo_id = "LangQuant/LQ-FSE-base"
|
| 66 |
+
|
| 67 |
+
# ๋ชจ๋ธ ๋ก๋
|
| 68 |
+
config = AutoConfig.from_pretrained(repo_id, trust_remote_code=True)
|
| 69 |
+
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)
|
| 70 |
+
tokenizer = AutoTokenizer.from_pretrained(repo_id)
|
| 71 |
+
model.eval()
|
| 72 |
+
|
| 73 |
+
# ์
๋ ฅ ํ
์คํธ
|
| 74 |
+
text = (
|
| 75 |
+
"์ผ์ฑ์ ์์ 2024๋
4๋ถ๊ธฐ ์ค์ ์ด ์์ฅ ์์์ ์ํํ๋ค. "
|
| 76 |
+
"๋ฉ๋ชจ๋ฆฌ ๋ฐ๋์ฒด ๊ฐ๊ฒฉ ์์น์ผ๋ก ์์
์ด์ต์ด ์ ๋ถ๊ธฐ ๋๋น 30% ์ฆ๊ฐํ๋ค. "
|
| 77 |
+
"HBM3E ์์ฐ์ด ๋ณธ๊ฒฉํ๋๋ฉด์ AI ๋ฐ๋์ฒด ์์ฅ ์ ์ ์จ์ด ํ๋๋ ์ ๋ง์ด๋ค."
|
| 78 |
+
)
|
| 79 |
+
|
| 80 |
+
# ๋ฌธ์ฅ ๋ถ๋ฆฌ ๋ฐ ํ ํฐํ
|
| 81 |
+
sentences = [s.strip() for s in re.split(r'(?<=[.!?])\s+', text.strip()) if s.strip()]
|
| 82 |
+
max_len, max_sent = config.max_length, config.max_sentences
|
| 83 |
+
|
| 84 |
+
padded = sentences[:max_sent]
|
| 85 |
+
num_real = len(padded)
|
| 86 |
+
while len(padded) < max_sent:
|
| 87 |
+
padded.append("")
|
| 88 |
+
|
| 89 |
+
ids_list, mask_list = [], []
|
| 90 |
+
for s in padded:
|
| 91 |
+
if s:
|
| 92 |
+
enc = tokenizer(s, max_length=max_len, padding="max_length", truncation=True, return_tensors="pt")
|
| 93 |
+
else:
|
| 94 |
+
enc = {"input_ids": torch.zeros(1, max_len, dtype=torch.long),
|
| 95 |
+
"attention_mask": torch.zeros(1, max_len, dtype=torch.long)}
|
| 96 |
+
ids_list.append(enc["input_ids"])
|
| 97 |
+
mask_list.append(enc["attention_mask"])
|
| 98 |
+
|
| 99 |
+
input_ids = torch.cat(ids_list).unsqueeze(0)
|
| 100 |
+
attention_mask = torch.cat(mask_list).unsqueeze(0)
|
| 101 |
+
doc_mask = torch.zeros(1, max_sent)
|
| 102 |
+
doc_mask[0, :num_real] = 1
|
| 103 |
+
|
| 104 |
+
# ์ถ๋ก
|
| 105 |
+
with torch.no_grad():
|
| 106 |
+
scores, role_logits = model(input_ids, attention_mask, doc_mask)
|
| 107 |
+
|
| 108 |
+
role_labels = config.role_labels
|
| 109 |
+
for i, sent in enumerate(sentences):
|
| 110 |
+
score = scores[0, i].item()
|
| 111 |
+
role = role_labels[role_logits[0, i].argmax().item()]
|
| 112 |
+
marker = "*" if score >= 0.5 else " "
|
| 113 |
+
print(f" {marker} [{score:.4f}] [{role:10s}] {sent}")
|
| 114 |
+
```
|
| 115 |
+
|
| 116 |
+
## Model Architecture
|
| 117 |
+
|
| 118 |
+
```
|
| 119 |
+
Input Sentences
|
| 120 |
+
โ
|
| 121 |
+
[klue/roberta-base] โ [CLS] embeddings per sentence
|
| 122 |
+
โ
|
| 123 |
+
[Inter-sentence Transformer] (2 layers, 8 heads)
|
| 124 |
+
โ
|
| 125 |
+
โโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโ
|
| 126 |
+
โ Binary Classifierโ Role Classifier โ
|
| 127 |
+
โ (representative?)โ (outlook/event/ โ
|
| 128 |
+
โ โ financial/risk) โ
|
| 129 |
+
โโโโโโโโโโโโโโโโโโโโดโโโโโโโโโโโโโโโโโโโโโโ
|
| 130 |
+
```
|
| 131 |
+
|
| 132 |
+
## Training
|
| 133 |
+
|
| 134 |
+
- Optimizer: AdamW (lr=2e-5, weight_decay=0.01)
|
| 135 |
+
- Scheduler: Linear warmup (10%)
|
| 136 |
+
- Loss: BCE (extraction) + CrossEntropy (role), role_weight=0.5
|
| 137 |
+
- Max sentence length: 128 tokens
|
| 138 |
+
- Max sentences per document: 30
|
| 139 |
+
|
| 140 |
+
## Files
|
| 141 |
+
|
| 142 |
+
- `model.py`: Model definition (DocumentEncoderConfig, DocumentEncoderForExtractiveSummarization)
|
| 143 |
+
- `config.json`: Model configuration
|
| 144 |
+
- `model.safetensors`: Model weights
|
| 145 |
+
- `inference_example.py`: Inference helper with usage example
|
| 146 |
+
- `convert_checkpoint.py`: Script to convert original .pt checkpoint
|
| 147 |
+
|
| 148 |
+
## Disclaimer (๋ฉด์ฑ
์กฐํญ)
|
| 149 |
+
|
| 150 |
+
- ๋ณธ ๋ชจ๋ธ์ **์ฐ๊ตฌ ๋ฐ ์ ๋ณด ์ ๊ณต ๋ชฉ์ **์ผ๋ก๋ง ์ ๊ณต๋ฉ๋๋ค.
|
| 151 |
+
- ๋ณธ ๋ชจ๋ธ์ ์ถ๋ ฅ์ **ํฌ์ ์กฐ์ธ, ๊ธ์ต ์๋ฌธ, ๋งค๋งค ์ถ์ฒ์ด ์๋๋๋ค.**
|
| 152 |
+
- ๋ชจ๋ธ์ ์์ธก ๊ฒฐ๊ณผ๋ฅผ ๊ธฐ๋ฐ์ผ๋ก ํ ํฌ์ ํ๋จ์ ๋ํด LangQuant ๋ฐ ๊ฐ๋ฐ์๋ **์ด๋ ํ ๋ฒ์ ์ฑ
์๋ ์ง์ง ์์ต๋๋ค.**
|
| 153 |
+
- ๋ชจ๋ธ์ ์ ํ์ฑ, ์์ ์ฑ, ์ ์์ฑ์ ๋ํด ๋ณด์ฆํ์ง ์์ผ๋ฉฐ, ์ค์ ํฌ์ ์์ฌ๊ฒฐ์ ์ ๋ฐ๋์ ์ ๋ฌธ๊ฐ์ ์กฐ์ธ์ ๊ตฌํ์๊ธฐ ๋ฐ๋๋๋ค.
|
| 154 |
+
- ๊ธ์ต ์์ฅ์ ๋ณธ์ง์ ์ผ๋ก ๋ถํ์คํ๋ฉฐ, ๊ณผ๊ฑฐ ๋ฐ์ดํฐ๋ก ํ์ต๋ ๋ชจ๋ธ์ด ๋ฏธ๋ ์ฑ๊ณผ๋ฅผ ๋ณด์ฅํ์ง ์์ต๋๋ค.
|
| 155 |
+
|
| 156 |
+
## Usage Restrictions (์ฌ์ฉ ์ ํ)
|
| 157 |
+
|
| 158 |
+
- **๊ธ์ง ์ฌํญ:**
|
| 159 |
+
- ๋ณธ ๋ชจ๋ธ์ ์ด์ฉํ ์์ธ ์กฐ์ข
, ํ์ ์ ๋ณด ์์ฑ ๋ฑ ๋ถ๋ฒ์ ๋ชฉ์ ์ ์ฌ์ฉ
|
| 160 |
+
- ์๋ํ๋ ํฌ์ ๋งค๋งค ์์คํ
์ ๋จ๋
์์ฌ๊ฒฐ์ ์๋จ์ผ๋ก ์ฌ์ฉ
|
| 161 |
+
- ๋ชจ๋ธ ์ถ๋ ฅ์ ์ ๋ฌธ ๊ธ์ต ์๋ฌธ์ธ ๊ฒ์ฒ๋ผ ์ 3์์๊ฒ ์ ๊ณตํ๋ ํ์
|
| 162 |
+
- **ํ์ฉ ์ฌํญ:**
|
| 163 |
+
- ํ์ ์ฐ๊ตฌ ๋ฐ ๊ต์ก ๋ชฉ์ ์ ์ฌ์ฉ
|
| 164 |
+
- ๊ธ์ต ํ
์คํธ ๋ถ์ ํ์ดํ๋ผ์ธ์ ๋ณด์กฐ ๋๊ตฌ๋ก ํ์ฉ
|
| 165 |
+
- ์ฌ๋ด ๋ฆฌ์์น/๋ถ์ ์
๋ฌด์ ์ฐธ๊ณ ์๋ฃ๋ก ํ์ฉ
|
| 166 |
+
- ์์
์ ์ฌ์ฉ ์ LangQuant์ ์ฌ์ ๋ฌธ์๋ฅผ ๊ถ์ฅํฉ๋๋ค.
|
| 167 |
+
|
| 168 |
+
## Contributors
|
| 169 |
+
|
| 170 |
+
- **[Taegyeong Lee](https://www.linkedin.com/in/taegyeong-lee/)** (taegyeong.leaf@gmail.com)
|
| 171 |
+
- **[Dong Young Kim](https://www.linkedin.com/in/dykim04/)** (dong-kim@student.42kl.edu.my) โ Ecole 42
|
| 172 |
+
- **[Seunghyun Hwang](https://www.linkedin.com/in/seung-hyun-hwang-53700124a/)** (hsh1030@g.skku.edu) โ DSSAL
|