Samiya Kashif
salakash
AI & ML interests
None yet
Organizations
Reproducibility packaging (big for arXiv credibility)
#45 opened 4 months ago
by
salakash
“Style strength” knob via LoRA scaling
1
#41 opened 4 months ago
by
jbakerx
Add structural tokens for literature
1
#43 opened 4 months ago
by
jbakerx
Add continuous evaluation + regression tests
1
#29 opened 5 months ago
by
jbakerx
change "lora_bias" to 'true'
1
#7 opened 5 months ago
by
jbakerx
Add Russian-language capability (two-stage LoRA)
1
#12 opened 5 months ago
by
jbakerx
Release two adapters instead of one
1
#14 opened 5 months ago
by
jbakerx
Improve long form coherence with “chapter packing”
1
#18 opened 5 months ago
by
jbakerx
Add a “modern-to-classical rewrite” mode
1
#21 opened 5 months ago
by
jbakerx
Add anti-quote-memorization checks
1
#23 opened 5 months ago
by
jbakerx
DAPT → SFT → DPO (3 step quality upgrade)
1
#24 opened 5 months ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
1
#26 opened 5 months ago
by
jbakerx
Add a lightweight style classifier for filtering
1
#27 opened 5 months ago
by
jbakerx
Quantization aware adapter testing
1
#30 opened 5 months ago
by
jbakerx
RAG for factual grounding (optional)
1
#31 opened 5 months ago
by
jbakerx
Add explicit “avoid anachronisms” behavior
1
#32 opened 5 months ago
by
jbakerx
Better segmentation: train on scenes, not entire books
1
#33 opened 5 months ago
by
jbakerx
Add a lightweight style classifier for filtering
1
#34 opened 5 months ago
by
jbakerx
Multi author literary adapters + author-mix control
1
#35 opened 4 months ago
by
jbakerx
Preference data bootstrapping (cheap but effective)
1
#36 opened 4 months ago
by
jbakerx