16 commits

Author	SHA1	Message	Date
51616	696b45c51b	icml rebuttal	2026-06-15 04:31:47 +00:00
51616	a074fd3305	self-gen data misaligned fixed + niah reproducible + vllm-tokenizers version combo	2025-10-08 05:17:50 +00:00
51616	39ed1b3d75	basic gradio app	2025-10-02 06:35:33 +00:00
51616	b6679ba755	iclr cleanup	2025-09-30 14:53:21 +00:00
51616	9d82014dc2	q gen can take ds_names + self_gen summ/struct/cot prob + ctx qa v3 data	2025-08-28 17:42:43 +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
51616	ea2abde3a1	gcp bucket watcher	2025-08-10 05:25:45 +00:00
51616	178e7165ea	per-rank bias + skip interleave if cached+ add bnb	2025-08-09 15:20:37 +00:00
Rujikorn Charakorn	891c0bd256	Refactor_and_improve_data (#7) ... * faster slice * add facts + ctx_qa * new configs * new scripts * intx_sft.py to train.py * add kaggle for downloading facts * max_new_tokens cli for eval * generate negative_nq * scripts + configs * default vals * max_val_samples_per_ds=500 * more efficient layer-to-layer ctx encoder * use_per_ctx_average_loss * faster processing * small exp distill * scripts * more robust watcher * per-module l1_norm avg * per-ctx average loss * clear_gpu	2025-08-04 20:52:37 +09:00
51616	63f02fb4a7	gemma can now gen with flash attn (revert transformers to 4.51.3)	2025-06-25 23:16:36 +09:00
51616	9ccc7c8f76	add opt-einsum	2025-06-23 15:35:01 +09:00
51616	36d78c827c	transformers ver + squad only example	2025-06-20 21:38:26 +09:00
51616	c71835daa9	hf transfer	2025-06-19 23:08:23 +09:00
51616	b61086034c	data exp + packing	2025-06-17 11:34:16 +00:00
51616	d1aecb6051	update installation	2025-06-03 07:03:28 +00:00
Rujikorn Charakorn	9f986cf938	rearrange + move to uv (#1)	2025-05-27 21:18:15 +09:00