doc-to-lora/src/ctx_to_lora
2025-09-04 21:18:47 +09:00
..
data toy ctx magic num eval upto 32k + remove configs 2025-09-01 05:57:06 +00:00
modeling AB scaler + use bias for generation 2025-09-04 21:15:42 +09:00
__init__.py monkey patch liger kernel for gemma-3-1b-it 2025-06-19 04:44:24 +09:00
configs.py emb rescale + alpha 1 2025-09-03 13:14:17 +09:00
eval_utils.py LoRA separate bias param + merger + toy ds (#15) 2025-08-29 11:55:24 +09:00
hooks.py rearrange + move to uv (#1) 2025-05-27 21:18:15 +09:00
metrics.py toy ctx nums and multi-lora training (#11) 2025-08-18 18:38:07 +09:00
model_loading.py magic alpha! 2025-09-03 17:43:44 +09:00
monkey_patch.py monkey patch liger kernel for gemma-3-1b-it 2025-06-19 04:44:24 +09:00
pooling.py rearrange + move to uv (#1) 2025-05-27 21:18:15 +09:00
trainer.py fix logging + l1norm div by num ctx (work correctly w/ grad accum) 2025-09-04 21:18:47 +09:00
utils.py fixing non-packed collator + packing working and trainable 2025-06-24 17:35:50 +09:00
viz_utils.py llm comparator 2025-06-17 11:35:04 +00:00