12 commits

Author	SHA1	Message	Date
51616	b6679ba755	iclr cleanup	2025-09-30 14:53:21 +00:00
Rujikorn Charakorn	c5e9bc769d	toy ctx nums and multi-lora training (#11) ... * multi-lora trainable toy number repeat dataset * per rank bias init * remove head_bias +simplify merge + skip perplexities metric * ctx_numbers train example * self-gen ctx numbers example	2025-08-18 18:38:07 +09:00
ShinnosukeUesakaSakana	d99fa8732b	Add distillation training (#5) ... - work with vllm self-gen data (everything is tokenized during self-gen) - fix chat template! - not use liger kernel for distillation (for both training and eval)	2025-07-29 15:32:06 +09:00
51616	f08831d957	qa data exp	2025-06-26 15:30:26 +09:00
51616	6039b7f1d8	gemm3-1b template	2025-06-25 23:21:32 +09:00
51616	13a062fad4	fix template for gemm3-1b	2025-06-25 23:20:53 +09:00
51616	b218df0feb	gemma 3	2025-06-17 11:35:12 +00:00
51616	73b12c77a9	fix chat template (include chat eos in labels)	2025-06-10 03:08:27 +00:00
51616	ad205ad02a	fix chat template (include chat eos in labels)	2025-06-10 03:08:16 +00:00
51616	a9a164e2de	clean up configs + scripts + chat_templates (+ %generation% tag)	2025-06-06 04:56:45 +00:00
51616	670809f555	webui working (not yet two loras)	2025-05-13 10:49:31 +00:00
51616	4f4aecdb00	add squad and gemma	2025-01-18 12:36:12 +00:00