16 Commits

Author	SHA1	Message	Date
turboderp	83baa98ed9	Add machine-parseable output to convert script	2024-05-20 01:49:34 +02:00
turboderp	750c85e2c7	Fixes to allow quantizing Granite	2024-05-09 02:31:21 +02:00
turboderp	740a19a27c	Optimize: More robust solver	2024-04-09 23:13:21 +02:00
turboderp	63394ab8a5	Optimizer: Add accuracy bias to first layer	2024-04-06 08:01:43 +02:00
turboderp	9c47269913	Add parallel decoder block	2024-03-19 18:20:44 +01:00
turboderp	0b05686e76	Refactor, clean up and consolidate architecture logic	2024-03-06 02:46:47 +01:00
turboderp	dce84866e1	Support for StarCoder2, initial	2024-03-05 21:20:29 +01:00
turboderp	d36077cf92	Fix converter	2023-12-28 10:11:45 +01:00
turboderp	d2753a29b8	Mixtral EXL2 support, initial	2023-12-16 16:50:50 +01:00
turboderp	39fd07083a	Add error norm	2023-12-13 02:20:25 +01:00
turboderp	0d63d6479c	Rework quantization and optimization	2023-12-13 01:00:11 +01:00
turboderp	2e91239571	New quant optimization procedure	2023-12-08 20:19:57 +01:00
turboderp	c7d1bc7ef0	TODO items	2023-10-11 23:44:04 +02:00
turboderp	a4f2663e31	Fix edge case in optimize.py	2023-09-18 20:06:39 +02:00
turboderp	47418c0c78	Allow optimizer to include larger matrices when minimizing the max error results in a bitrate < target	2023-09-18 18:24:30 +02:00
turboderp	bb83469574	Initial commit	2023-08-30 11:05:23 +02:00