STINER/.gitignore at main · ChammakhYasir/STINER · GitHub

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
# Data - RAW and annotation files (not needed for reproduction)
data/raw/
data/label_studio/
data/intermediate/

# Data - CSV files in data root (not needed for reproduction)
data/*.csv
data/tco_cache.json

# Data - Keep only processed splits and tweet IDs for reproduction
!data/processed/
!data/processed/train.json
!data/processed/val.json
!data/processed/test.json
!data/tweet_ids.txt

# Models (too large for git)
models/encoders/*/checkpoint-*/
models/encoders/*/optimizer.pt
models/encoders/*/model.safetensors
models/encoders_crf/*/model.pt

# LLM fine-tuned models (large files)
models/llm_finetuned/checkpoint-*/
models/llm_finetuned/adapter_model.safetensors
models/gemma_finetuned/checkpoint-*/
models/gemma_finetuned/adapter_model.safetensors
models/qwen_finetuned/checkpoint-*/
models/qwen_finetuned/adapter_model.safetensors

# Keep model configs and tokenizers (small, needed)
!models/encoders/*/config.json
!models/encoders/*/tokenizer*.json
!models/encoders/*/vocab.txt
!models/encoders_crf/*/label_map.json
!models/encoders_crf/*/tokenizer/

# Inference results (large)
inference/

# Python
__pycache__/
*.pyc
*.pyo
*.pyd
.Python
.venv/
venv/
env/

# Jupyter
.ipynb_checkpoints/
*.ipynb_checkpoints

# IDE
.vscode/
.idea/
*.swp
*.swo

# OS
.DS_Store
Thumbs.db

# Environment
.env
*.log

# Cache
.cache/
*.cache