Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
ruwwww
/
faruq-alignment-models
Like
1
Text Generation
Safetensors
Indonesian
legal
indonesia
mahkamah-agung
sft
qlora
gemma-4
qwen
alignment
ratio-decidendi
dictum
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
faruq-alignment-models
35 GB
Ctrl+K
Ctrl+K
1 contributor
History:
83 commits
ruwwww
README: SFT 16k adapters and zero-shot vs SFT metrics (510 test cases); mark old onboarding guide as stale
2a045ef
verified
1 day ago
docs
README: SFT 16k adapters and zero-shot vs SFT metrics (510 test cases); mark old onboarding guide as stale
1 day ago
evaluations
evaluations: SFT 16k vs zero-shot ROUGE on 510 test cases (metrics only, no case text)
2 days ago
models
rosy-thesis-sft-16k-gemma4_12b: adapter + epoch checkpoints 575, 1150, 1725, 2300, 2875
3 days ago
scripts
feat: upload SFT v2 1-epoch and 5-epoch model adapters with reproduction configs and infer script
25 days ago
wheels
Upload pre-built vLLM wheel for Python 3.13 and CUDA 12.8 (A100)
13 days ago
.gitattributes
Safe
13 kB
rosy-thesis-sft-16k-gemma4_12b: adapter + epoch checkpoints 575, 1150, 1725, 2300, 2875
3 days ago
README.md
14.6 kB
README: SFT 16k adapters and zero-shot vs SFT metrics (510 test cases); mark old onboarding guide as stale
1 day ago
