Add explicit “avoid anachronisms” behavior
#39 opened about 1 hour ago
by
jbakerx
Curriculum learning by length
#38 opened about 1 hour ago
by
jbakerx
DAPT → SFT → DPO (3-step quality upgrade)
#37 opened about 1 hour ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
#36 opened about 1 hour ago
by
jbakerx
Multi author literary adapters + author-mix control
#35 opened about 1 hour ago
by
jbakerx
Add a lightweight style classifier for filtering
#34 opened 2 days ago
by
jbakerx
Better segmentation: train on scenes, not entire books
#33 opened 2 days ago
by
jbakerx
Add explicit “avoid anachronisms” behavior
#32 opened 2 days ago
by
jbakerx
RAG for factual grounding (optional)
#31 opened 2 days ago
by
jbakerx
Quantization aware adapter testing
#30 opened 3 days ago
by
jbakerx
Add continuous evaluation + regression tests
#29 opened 3 days ago
by
jbakerx
Better segmentation: train on scenes, not entire books
#28 opened 4 days ago
by
jbakerx
Add a lightweight style classifier for filtering
#27 opened 4 days ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
#26 opened 4 days ago
by
jbakerx
Multi-author literary adapters + author-mix control
#25 opened 4 days ago
by
jbakerx
DAPT → SFT → DPO (3 step quality upgrade)
#24 opened 4 days ago
by
jbakerx
Add anti-quote-memorization checks
#23 opened 5 days ago
by
jbakerx
Shipping/serving improvements
#22 opened 5 days ago
by
jbakerx
Add a “modern-to-classical rewrite” mode
#21 opened 5 days ago
by
jbakerx
Create multiple adapters by sub skill
#20 opened 5 days ago
by
jbakerx
Add “character + POV” conditioning
#19 opened 7 days ago
by
jbakerx
Improve long form coherence with “chapter packing”
#18 opened 7 days ago
by
jbakerx
Use a Russian-friendly tokenizer strategy
#17 opened 7 days ago
by
jbakerx
Improve dataset hygiene for literary corpora
#16 opened 7 days ago
by
jbakerx
Evaluation you can publish in a follow-up paper
#15 opened 7 days ago
by
jbakerx
Release two adapters instead of one
#14 opened 7 days ago
by
jbakerx
Dual-lingual style transfer (English ↔ Russian)
#13 opened 7 days ago
by
jbakerx
Add Russian-language capability (two-stage LoRA)
#12 opened 7 days ago
by
jbakerx
Improve dataset hygiene for literary corpora
#11 opened 7 days ago
by
jbakerx
🚩 Report: Spam
1
#9 opened 8 days ago
by
diimdeep
change "lora_bias" to 'true'
#7 opened about 1 month ago
by
jbakerx
Update README.md
#5 opened about 1 month ago
by
jbakerx
Languages spoken
1
#2 opened about 1 month ago
by
mirix
Update README.md (Remove Duplicates)
#1 opened about 1 month ago
by
qpqpqpqpqpqp