1501 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Jake Poznanski	b2a950f9f4	1 epoich custom trainer	2025-07-21 22:34:35 +00:00
Jake Poznanski	28a207b912	Grok was asked to drop the hf trainer and implement it custom	2025-07-21 22:33:50 +00:00
Jake Poznanski	da6bc458cd	Fix for compresor	2025-07-21 22:21:04 +00:00
Jake Poznanski	eb200e71c6	Fixing some default configs on quantizer	2025-07-21 21:43:33 +00:00
Jake Poznanski	0aa74795d3	More calibration samples by default	2025-07-21 21:33:43 +00:00
Jake Poznanski	6e480129d1	Trying out an idea for dataset augmentation	2025-07-19 15:27:53 +00:00
Jake Poznanski	df960cbc15	2 epoch config just to try	2025-07-18 23:25:27 +00:00
Jake Poznanski	a326c965dd	Default to 1288	2025-07-17 19:46:35 +00:00
Jake Poznanski	b88c71e00c	Rounding to better image size, full soups	2025-07-16 20:41:35 +00:00
Jake Poznanski	75bfa6a603	Adding full soup configs	2025-07-16 20:32:58 +00:00
Jake Poznanski	0f733ffc30	FIxes to compare vllm script	2025-07-16 19:58:35 +00:00
Jake Poznanski	16145a4b32	Need accelerate	2025-07-16 18:51:37 +00:00
Jake Poznanski	4785759ba1	Adding some souping suppor to prepare checkpoint	2025-07-16 18:16:47 +00:00
Jake Poznanski	2b638559a1	Compare has better downloader	2025-07-16 17:56:39 +00:00
Jake Poznanski	0b40bd3528	Better docker ignore	2025-07-16 17:36:32 +00:00
Jake Poznanski	d21a164bac	Fixing async stuff	2025-07-16 17:20:07 +00:00
Jake Poznanski	3ca305d0b8	Adding some souping configs	2025-07-16 03:42:55 +00:00
Jake Poznanski	c0bf3105df	Fixing import	2025-07-16 03:36:12 +00:00
Jake Poznanski	31c834dcdd	Constants	2025-07-16 02:15:17 +00:00
Jake Poznanski	5ea4e8a6e2	Compare vllm script	2025-07-15 22:55:49 +00:00
Jake Poznanski	939a76a4d1	Adding a compare vllm checkpoint script	2025-07-15 22:38:55 +00:00
Jake Poznanski	24608956a0	Working on comparing to vllm	2025-07-15 22:21:54 +00:00
Jake Poznanski	e6c98236b6	Adding more pipeline retry stats, compress code fixed	2025-07-15 21:41:10 +00:00
Jake Poznanski	4dbbf91e1c	Compression script	2025-07-15 21:26:15 +00:00
Jake Poznanski	feb2daba9a	Adjus config	2025-07-15 21:06:53 +00:00
Jake Poznanski	022f437b41	w8a8-int8 version	2025-07-15 21:02:35 +00:00
Jake Poznanski	5a4a836be7	Calibration	2025-07-15 20:59:33 +00:00
Jake Poznanski	9115a02c67	Fixes	2025-07-15 20:46:40 +00:00
Jake Poznanski	4b0960bb69	Test	2025-07-15 20:43:43 +00:00
Jake Poznanski	ee69faa87d	Dataset	2025-07-15 20:39:13 +00:00
Jake Poznanski	bd92f08cd7	Errors propagated	2025-07-15 20:32:16 +00:00
Jake Poznanski	fcd373d831	Calibration stuff	2025-07-15 20:27:05 +00:00
Jake Poznanski	2218bf8460	Merge branch 'jakep/new_trainer_vllm092' into jakep/new_trainer	2025-07-15 19:51:29 +00:00
Jake Poznanski	b5f480d19d	Working on calibration set for compressor, seems like qwen2.5 is not working	2025-07-15 18:59:48 +00:00
Jake Poznanski	e77bcd20ab	Upping vllm versions	2025-07-15 18:43:38 +00:00
Jake Poznanski	3f9fc8bd1b	Better compressor hopefully	2025-07-15 18:08:17 +00:00
Jake Poznanski	287c8278f5	Starting to cleanup and merge yaml front matter stuff in	2025-07-15 18:00:01 +00:00
Jake Poznanski	1092213c5f	Merge branch 'jakep/new_traininer_nojson_newprompt' into jakep/new_trainer	2025-07-15 17:44:55 +00:00
Jake Poznanski	679063aba5	Adding some more logging to compressor	2025-07-15 17:42:33 +00:00
Jake Poznanski	43ae28dde4	Prepare checkpoint works for older models too	2025-07-14 21:30:32 +00:00
Jake Poznanski	f306a52fe1	Compress fix	2025-07-14 21:16:48 +00:00
Jake Poznanski	f014c2aaf9	Need to reserve all 8 gpus for reliable performance benchmark, even if you only use 1	2025-07-14 21:02:14 +00:00
Jake Poznanski	01360ba21d	Compressor script	2025-07-14 20:56:51 +00:00
Jake Poznanski	1ede76d0b2	Cleaning up compress and prepare checkpoint scripts	2025-07-14 20:36:20 +00:00
Jake Poznanski	2674162d02	New prompt test	2025-07-14 17:35:29 +00:00
Jake Poznanski	a5a0cd7478	Trying a few more configs	2025-07-11 20:19:48 +00:00
Jake Poznanski	384a1b19c7	Qwen 2 config too	2025-07-11 17:20:59 +00:00
Jake Poznanski	24a3fb87e8	128batch config, wsd config	2025-07-11 17:19:02 +00:00
Jake Poznanski	0c773c40af	Let's do a 1280 no anchor yaml	2025-07-10 21:44:39 +00:00
Jake Poznanski	65d0edcaae	Adding guided decoding option	2025-07-10 15:13:26 +00:00