Add “compression mode”
#49 opened about 2 months ago
by
jbakerx
Clean dialogue punctuation and attribution
#48 opened about 2 months ago
by
jbakerx
Add continuous evaluation + regression tests
#47 opened about 2 months ago
by
jbakerx
Cross-lingual style alignment with parallel passages
#46 opened about 2 months ago
by
jbakerx
Reproducibility packaging (big for arXiv credibility)
#45 opened about 2 months ago
by
salakash
Negative sampling: teach what not to do
#44 opened 3 months ago
by
jbakerx
Add structural tokens for literature
1
#43 opened 3 months ago
by
jbakerx
Hierarchical prompting: outline → draft → polish
#42 opened 3 months ago
by
jbakerx
“Style strength” knob via LoRA scaling
1
#41 opened 3 months ago
by
jbakerx
Adapter routing (Mixture of adapters)
#40 opened 3 months ago
by
jbakerx
Add explicit “avoid anachronisms” behavior
1
#39 opened 3 months ago
by
jbakerx
Curriculum learning by length
1
#38 opened 3 months ago
by
jbakerx
DAPT → SFT → DPO (3-step quality upgrade)
1
#37 opened 3 months ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
1
#36 opened 3 months ago
by
jbakerx
Multi author literary adapters + author-mix control
1
#35 opened 3 months ago
by
jbakerx
Add a lightweight style classifier for filtering
1
#34 opened 3 months ago
by
jbakerx
Better segmentation: train on scenes, not entire books
1
#33 opened 3 months ago
by
jbakerx
Add explicit “avoid anachronisms” behavior
1
#32 opened 3 months ago
by
jbakerx
RAG for factual grounding (optional)
1
#31 opened 3 months ago
by
jbakerx
Quantization aware adapter testing
1
#30 opened 3 months ago
by
jbakerx
Add continuous evaluation + regression tests
1
#29 opened 3 months ago
by
jbakerx
Better segmentation: train on scenes, not entire books
#28 opened 3 months ago
by
jbakerx
Add a lightweight style classifier for filtering
1
#27 opened 3 months ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
1
#26 opened 3 months ago
by
jbakerx
Multi-author literary adapters + author-mix control
#25 opened 3 months ago
by
jbakerx
DAPT → SFT → DPO (3 step quality upgrade)
1
#24 opened 3 months ago
by
jbakerx
Add anti-quote-memorization checks
1
#23 opened 3 months ago
by
jbakerx
Shipping/serving improvements
#22 opened 3 months ago
by
jbakerx
Add a “modern-to-classical rewrite” mode
1
#21 opened 3 months ago
by
jbakerx
Create multiple adapters by sub skill
#20 opened 3 months ago
by
jbakerx
Add “character + POV” conditioning
#19 opened 3 months ago
by
jbakerx
Improve long form coherence with “chapter packing”
1
#18 opened 3 months ago
by
jbakerx
Use a Russian-friendly tokenizer strategy
#17 opened 3 months ago
by
jbakerx
Improve dataset hygiene for literary corpora
#16 opened 3 months ago
by
jbakerx
Evaluation you can publish in a follow-up paper
#15 opened 3 months ago
by
jbakerx
Release two adapters instead of one
1
#14 opened 3 months ago
by
jbakerx
Dual-lingual style transfer (English ↔ Russian)
#13 opened 3 months ago
by
jbakerx
Add Russian-language capability (two-stage LoRA)
1
#12 opened 3 months ago
by
jbakerx
Improve dataset hygiene for literary corpora
#11 opened 3 months ago
by
jbakerx
🚩 Report: Spam
1
#9 opened 3 months ago
by
diimdeep
change "lora_bias" to 'true'
1
#7 opened 4 months ago
by
jbakerx
Update README.md
#5 opened 4 months ago
by
jbakerx
Languages spoken
1
#2 opened 4 months ago
by
mirix
Update README.md (Remove Duplicates)
#1 opened 4 months ago
by
qpqpqpqpqpqp