Commit Graph

161 Commits

Author SHA1 Message Date
Concedo b0b131499f Merge branch 'master' into concedo_experimental
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	tests/test-tokenizer-0.cpp
2023-07-11 16:12:15 +08:00
Concedo 9324cb804a reimplemented save and load 2023-07-10 22:49:27 +08:00
Concedo 27a0907cfa backport MM256_SET_M128I to ggml_v2, updated lite, added support for selecting the GPU for cublas 2023-07-06 22:33:46 +08:00
Concedo 220aa707e6 Merge branch 'master' into concedo_experimental
# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	pocs/vdot/q8dot.cpp
#	pocs/vdot/vdot.cpp
#	scripts/sync-ggml.sh
#	tests/test-grad0.c
#	tests/test-quantize-fns.cpp
#	tests/test-quantize-perf.cpp
2023-07-06 15:40:40 +08:00
Concedo eda663f15f update lite and up ver 2023-07-01 00:15:26 +08:00
Concedo 746f5fa9e9 update lite 2023-06-29 16:44:39 +08:00
Concedo d2034ced7b Merge branch 'master' into concedo_experimental
# Conflicts:
#	README.md
#	build.zig
#	flake.nix
#	tests/test-grad0.c
#	tests/test-sampling.cpp
#	tests/test-tokenizer-0.cpp
2023-06-25 17:01:15 +08:00
Concedo 537ff22ec9 fixed a bug with token timings, updated lite 2023-06-20 20:41:42 +08:00
Concedo 8e2dc19dc6 updated tokenizer, added support for scratch buffers for neox and gpt2 2023-06-19 21:29:06 +08:00
Concedo cb6daa3171 updated lite 2023-06-19 11:51:23 +08:00
Concedo 8775dd99f4 various debug logging improvements 2023-06-18 15:24:58 +08:00
Concedo 795b35546b updated lite 2023-06-17 19:57:09 +08:00
Concedo ae88eec40b updated lite 2023-06-16 16:27:23 +08:00
Concedo 8ff35ef944 updated lite 2023-06-15 12:13:55 +08:00
Concedo f345347e5c updated lite 2023-06-13 20:44:22 +08:00
Concedo 0c9cd39259 lowered streaming tickrate for greater efficiency 2023-06-10 22:12:01 +08:00
Concedo 375540837e updated lite 2023-06-10 19:16:29 +08:00
Concedo 6635f7efce updated lite 2023-06-08 00:20:32 +08:00
Concedo c046db5197 lite bugfixes, buffer size changes, fixed a topk bug. 2023-06-06 22:38:25 +08:00
Concedo 2e5edc80e0 updated lite 2023-06-05 23:56:24 +08:00
Concedo 6f66e4c4a5 updated lite 2023-06-04 22:27:15 +08:00
Concedo 144d8a8312 updated lite 2023-06-02 12:19:51 +08:00
Concedo 49272e3c53 adjusted defaults 2023-06-01 20:03:44 +08:00
Concedo 234270bd83 back to 32 block size, not better 2023-06-01 00:14:22 +08:00
Concedo 32dada5e5f updated lite 2023-05-31 17:52:09 +08:00
Concedo ef16d09a51 fix for older gcc, updated lite 2023-05-29 18:54:15 +08:00
Concedo 28f1196f65 adjust default rep pen range 2023-05-28 19:36:21 +08:00
Concedo 7d159bacd7 updated kobold lite 2023-05-28 11:23:20 +08:00
Concedo 8b8f2f4cf5 up ver to 1.25.1 2023-05-25 14:49:30 +08:00
Concedo bf482d1786 revert klite newline bug, trying to add win7 support 2023-05-24 22:21:01 +08:00
Concedo b314cbfb60 updated lite to support variable streaming lengths 2023-05-24 11:28:35 +08:00
Concedo 0c0009e4b4 updated lite 2023-05-23 23:18:52 +08:00
Concedo 7894e85788 fixed a bug in previous klite 2023-05-22 21:54:24 +08:00
Concedo a05da31fe7 updated embedded lite 2023-05-22 20:58:54 +08:00
Concedo 24127ebf98 updated lite, fixed some encoding issues 2023-05-21 17:29:00 +08:00
Concedo 60ee00428b updated lite 2023-05-17 10:26:36 +08:00
Concedo 017023e477 updated kobold lite 2023-05-13 12:12:20 +08:00
Concedo e47f7ade05 updated kobold lite, patch oom errors 2023-05-09 19:16:45 +08:00
Concedo c8f7eeb7fd update kobold lite 2023-05-04 14:43:35 +08:00
Concedo 9a9b217e57 updated embedded kobold lite with multiuser chat 2023-05-02 18:18:05 +08:00
Concedo 0703cdf2eb remove cloudflare insights 2023-05-02 00:38:10 +08:00
Concedo e8a389f85b updated kobold lite, added debug mode, changed streaming mode to now use the same url when launching 2023-04-28 11:41:03 +08:00
Concedo 137efe2b8f updated embedded kobold lite, force streaming mode if stream flag is used 2023-04-27 17:16:55 +08:00
Concedo b53c5e7c80 update kobold lite 2023-04-22 16:04:43 +08:00
Concedo ea01771dd5 rwkv is done 2023-04-18 20:55:01 +08:00
Concedo c200b674f4 updated kobold lite, work on rwkv, added exe path to model load params, added launch parameter 2023-04-18 17:36:44 +08:00
Concedo 8e923dc6e9 updated kobold lite 2023-04-17 21:33:57 +08:00
Concedo 763ad172c0 arranged files, updated kobold lite, modified makefile for extra link args on linux, started RWKV implementation 2023-04-17 17:31:45 +08:00
Concedo 9581171a9f updated embedded lite again 2023-04-16 22:42:51 +08:00
Concedo c757fbee1d fixes to stopper tokens, fixed BLAS mode for GPT2 and GPTJ, updated kobold lite 2023-04-16 21:54:18 +08:00