madcat-os/lora
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5 Commits 1 Branch 0 Tags
122e73860bd01280d00ec32a657f20515385fb62
Commit Graph

5 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
marauder-actual 122e73860b feat: tts-norm LoRA — dataset generator + training script 
gen_tts_dataset.py: 4960 synthetic examples, 22 categories (numbers,
currencies, dates, times, temperatures, acronyms, NATO phonetic, URLs,
markdown, etc). Bilingual EN/PL with explicit [lang] tag prefix.

train_tts_norm.py: Unsloth LoRA training for Qwen2.5-7B-Instruct.
Rank 16, 3 epochs, packing, max_seq 768. Trained on H100 in 20m38s,
final loss 0.091. Adapter: 154MB.
 2026-05-26 00:14:51 +02:00
marauder-actual 8137d278db fix: parse tool_call arguments from JSON string to dict for Qwen3.5 template 2026-05-25 19:16:07 +02:00
marauder-actual 4476520d5c v3 dataset (582 ex, 14% direct) + Qwen3.5-27B training script 2026-05-25 18:57:17 +02:00
marauder-actual 5deb9bd2b4 docs: bt7274 persona, specialist plan, tts-clean LoRA 2026-05-25 16:40:09 +02:00
madcat 9bcf1c2d9a init: bt7274 lora training — v1 adapter, v2 dataset (500 examples), justfile 2026-05-25 16:37:30 +02:00