Commit Graph

240 Commits

Author SHA1 Message Date
Ettore Di Giacinto
0eac0402e1
feat: backends improvements (#778) 2023-07-21 20:55:49 +02:00
Ettore Di Giacinto
982a7e86a8 feat: add huggingface embeddings backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 22:10:42 +02:00
Ettore Di Giacinto
5ce5f87a26
fix: move metal file to grpcs assets (#777)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 22:00:07 +02:00
ci-robbot [bot]
71ac331f90
⬆️ Update nomic-ai/gpt4all (#775)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-20 01:22:44 +02:00
Ettore Di Giacinto
3feb632eb4
refactor: rename "llama-master" and "llama" (#776)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-20 00:36:16 +02:00
ci-robbot [bot]
a38dc497b2
⬆️ Update go-skynet/go-llama.cpp (#770)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-19 19:44:33 +02:00
ci-robbot [bot]
28ed52fa94
⬆️ Update nomic-ai/gpt4all (#769)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-19 19:44:21 +02:00
Enzo Einhorn
e995b95c94
[build] pass build type to cmake on libtransformers.a build (#741)
Co-authored-by: Enzo Einhorn <enzo.einhorn@hiventive.com>
2023-07-18 19:04:19 +02:00
ci-robbot [bot]
3c6b798522
⬆️ Update nomic-ai/gpt4all (#759)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-17 23:58:40 +02:00
ci-robbot [bot]
c18770a61a
⬆️ Update go-skynet/go-bert.cpp (#758)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-17 23:58:25 +02:00
Ettore Di Giacinto
6352448b72
feat: add llama-master backend (#752)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-17 23:58:15 +02:00
ci-robbot [bot]
27ef8b1eb7
⬆️ Update go-skynet/go-ggml-transformers.cpp (#711)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-16 09:57:16 +02:00
ci-robbot [bot]
c00435d72b
⬆️ Update nomic-ai/gpt4all (#735)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-16 09:57:00 +02:00
ci-robbot [bot]
accd9f9044
⬆️ Update donomii/go-rwkv.cpp (#750)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-15 22:52:45 +02:00
Ettore Di Giacinto
f193f56564 fix: fix copy
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
c0a91ab548 fix: fix LDFLAGS for rwkv.cpp
Previously the libs were added by other deps that made the linker add
those as well (by chance).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
26e510bf28 fix: Makefile
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
7f3de3ca4a fix: fix makefile error
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
1d0ed95a54 feat: move other backends to grpc
This finally makes everything more consistent

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
f2f1d7fe72 feat: use gRPC for transformers
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
ae533cadef feat: move gpt4all to a grpc service
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
58f6aab637 feat: move llama to a grpc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
Ettore Di Giacinto
b816009db0 feat: add falcon ggllm via grpc client
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2023-07-15 01:19:43 +02:00
ci-robbot [bot]
a84dee1be1
⬆️ Update nomic-ai/gpt4all (#705)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-07-09 16:55:56 +02:00
mudler
c4495ad8f2 invoke go mod clean before rebuilds 2023-07-05 18:24:55 +02:00
mudler
1668489b00 Add comments 2023-07-04 19:02:02 +02:00
mudler
7dd292cbb3 feat: add a way to test grammar from forks 2023-07-04 18:58:19 +02:00
mudler
a5b64b6a41 wip: test go-llama.cpp version
It also needs a llama.cpp with grammar branch + rebased on current
master
2023-07-04 18:58:19 +02:00
mudler
6d19a8bdb5 fix: copy git to correctly display version in /version 2023-07-04 18:58:19 +02:00
Ettore Di Giacinto
70674d3c58
fix(deps): bump go-llama.cpp (#719)
Signed-off-by: mudler <mudler@localai.io>
2023-07-03 00:17:48 +02:00
ci-robbot [bot]
3829aba869
⬆️ Update nomic-ai/gpt4all (#704)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-30 10:30:39 +02:00
ci-robbot [bot]
e3db6496d7
⬆️ Update go-skynet/go-llama.cpp (#697)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-28 23:43:29 +02:00
ci-robbot [bot]
1e6542a5ca
⬆️ Update ggerganov/whisper.cpp (#696)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-28 23:42:57 +02:00
ci-robbot [bot]
218e7bc8df
⬆️ Update nomic-ai/gpt4all (#691)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-28 23:42:46 +02:00
ci-robbot [bot]
69367a7948
⬆️ Update go-skynet/go-ggml-transformers.cpp (#692)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-27 23:54:51 +02:00
ci-robbot [bot]
85a38a8122
⬆️ Update go-skynet/go-llama.cpp (#690)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-27 23:48:52 +02:00
ci-robbot [bot]
85eea1189e
⬆️ Update ggerganov/whisper.cpp (#682)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-27 09:01:09 +02:00
ci-robbot [bot]
ed2344ab9b
⬆️ Update nomic-ai/gpt4all (#681)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-27 09:00:57 +02:00
Ettore Di Giacinto
3593cb0c87
feat: update llama, enable NUMA (#684) 2023-06-27 09:00:10 +02:00
Samuel Maynard
e130b208ab
Docker preserve sources (#658) 2023-06-26 22:34:03 +02:00
Ettore Di Giacinto
d3a486a4f8
feat: Add '/version' endpoint and display it in the CLI (#679) 2023-06-26 15:12:43 +02:00
ci-robbot [bot]
a1ed6fbd96
⬆️ Update ggerganov/whisper.cpp (#672)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-26 12:26:02 +02:00
ci-robbot [bot]
0ba94bf33f
⬆️ Update nomic-ai/gpt4all (#668)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-25 09:26:17 +02:00
ci-robbot [bot]
be1667c387
⬆️ Update nomic-ai/gpt4all (#657)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-24 08:33:52 +02:00
ci-robbot [bot]
eb39d908d0
⬆️ Update go-skynet/go-llama.cpp (#634)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-24 08:33:40 +02:00
ci-robbot [bot]
55cf9d5792
⬆️ Update nomic-ai/gpt4all (#650)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-22 17:53:32 +02:00
Ettore Di Giacinto
a7bb029d23
feat: add tts with go-piper (#649)
Signed-off-by: mudler <mudler@localai.io>
2023-06-22 17:53:10 +02:00
ci-robbot [bot]
cc31c58235
⬆️ Update go-skynet/go-ggml-transformers.cpp (#644)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-21 08:58:20 +02:00
ci-robbot [bot]
445067f6ad
⬆️ Update donomii/go-rwkv.cpp (#600)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-21 08:57:15 +02:00
ci-robbot [bot]
11bfd0de76
⬆️ Update nomic-ai/gpt4all (#635)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-21 08:56:41 +02:00
ci-robbot [bot]
d0025a7483
⬆️ Update go-skynet/go-ggml-transformers.cpp (#633)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-20 08:47:21 +02:00
ci-robbot [bot]
db0b29be51
⬆️ Update nomic-ai/gpt4all (#628)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-20 00:12:24 +02:00
ci-robbot [bot]
1766de814c
⬆️ Update go-skynet/go-ggml-transformers.cpp (#619)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-18 23:49:38 +02:00
ci-robbot [bot]
0b351d6da2
⬆️ Update nomic-ai/gpt4all (#613)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-18 23:48:07 +02:00
Ettore Di Giacinto
d3d3187e51
feat: fix CUDA images and update go-llama to use full GPU offloading (#618)
Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: mudler <mudler@localai.io>
2023-06-18 08:27:29 +02:00
Ettore Di Giacinto
6c94f3cd67
Revert "Docker preserve sources" (#620) 2023-06-17 23:22:04 +02:00
Ettore Di Giacinto
1b7990d5d9
deps: switch back to nomic-ai/gpt4all (#595) 2023-06-14 18:07:05 +02:00
Samuel Maynard
7b9dcb05d4
Docker preserve sources (#590) 2023-06-14 13:26:27 +02:00
Ettore Di Giacinto
e37361985c
deps: update gpt4all bindings, fix search path on new versions (#592) 2023-06-14 13:24:53 +02:00
ci-robbot [bot]
467e88d305
⬆️ Update donomii/go-rwkv.cpp (#527)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-14 12:56:20 +02:00
ci-robbot [bot]
f98680a18a
⬆️ Update go-skynet/go-llama.cpp (#584)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-13 23:05:03 +02:00
ci-robbot [bot]
6306885fe7
⬆️ Update go-skynet/go-llama.cpp (#561)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-11 15:44:06 +02:00
Ettore Di Giacinto
2a11f16c0f
fix: copy metal file from build (#564) 2023-06-11 01:07:39 +02:00
ci-robbot [bot]
897ac6e4e5
⬆️ Update go-skynet/go-ggml-transformers.cpp (#562)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-11 01:01:46 +02:00
ci-robbot [bot]
e6c8ebb65c
⬆️ Update go-skynet/go-llama.cpp (#554)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-10 01:35:58 +02:00
ci-robbot [bot]
437f563128
⬆️ Update go-skynet/go-bert.cpp (#540)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-10 00:09:14 +02:00
ci-robbot [bot]
6bb562272d
⬆️ Update go-skynet/go-llama.cpp (#546)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-09 01:13:15 +02:00
ci-robbot [bot]
806e4c3a63
⬆️ Update go-skynet/go-ggml-transformers.cpp (#539)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-09 00:19:58 +02:00
Ettore Di Giacinto
c9bbba4872
tests: add llama tests with openllama (#538)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-08 00:36:11 +02:00
Ettore Di Giacinto
5abbb134d9
feat: extend model configuration for llama.cpp (#536) 2023-06-07 21:46:19 +02:00
ci-robbot [bot]
2630e251ce
⬆️ Update ggerganov/whisper.cpp (#520)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-06 19:16:42 +02:00
ci-robbot [bot]
0909a0637e
feat: update llama.cpp to support k-quants (#521)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-06 18:15:17 +02:00
Ettore Di Giacinto
d62aef2016
feat: add experimental support for falcon-7b (#516)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-06 17:23:19 +02:00
ci-robbot [bot]
25e9483add
⬆️ Update donomii/go-rwkv.cpp (#511)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-06 16:02:09 +02:00
ci-robbot [bot]
2e916abe15
⬆️ Update go-skynet/go-llama.cpp (#512)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-06 00:35:01 +02:00
Ettore Di Giacinto
b447a2a719
feat: support upscaled image generation with esrgan (#509) 2023-06-05 17:21:38 +02:00
Ettore Di Giacinto
ec4fd1d219
fix gpt4all, add metal GPU support (#507) 2023-06-05 14:26:20 +02:00
Ettore Di Giacinto
b503725dc7
fix: downgrade gpt4all (#503)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-05 09:42:50 +02:00
ci-robbot [bot]
e873fc7b71
⬆️ Update go-skynet/go-ggml-transformers.cpp (#501)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-05 00:07:48 +02:00
Ettore Di Giacinto
4ddc956462
deps: update rwkv, switch back to upstream (#494) 2023-06-04 17:25:35 +02:00
ci-robbot [bot]
b64c1d8ac1
⬆️ Update nomic-ai/gpt4all (#488)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-04 01:56:59 +02:00
ci-robbot [bot]
05edf59c91
⬆️ Update nomic-ai/gpt4all (#483)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-03 18:30:30 +02:00
ci-robbot [bot]
b9f1f85433
⬆️ Update go-skynet/go-llama.cpp (#482)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-03 18:30:18 +02:00
ci-robbot [bot]
29856f7527
⬆️ Update nomic-ai/gpt4all (#479)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-03 14:25:42 +02:00
Ettore Di Giacinto
e875c1f64a
fix: fix the make run target (#476)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-02 09:57:01 +02:00
Ettore Di Giacinto
19f92d7d55
fix: Bump and fix rwkv build (#475) 2023-06-02 08:53:57 +02:00
ci-robbot [bot]
a63d6f6364
⬆️ Update ggerganov/whisper.cpp (#473)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-01 23:44:05 +02:00
ci-robbot [bot]
4422ca2235
⬆️ Update go-skynet/go-ggml-transformers.cpp (#459)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-01 23:43:15 +02:00
Ettore Di Giacinto
78ad4813df
feat: Update gpt4all, support multiple implementations in runtime (#472)
Signed-off-by: mudler <mudler@mocaccino.org>
2023-06-01 23:38:52 +02:00
ci-robbot [bot]
5c018c0437
⬆️ Update ggerganov/whisper.cpp (#468)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-01 16:23:16 +02:00
ci-robbot [bot]
c5cb2ff268
⬆️ Update go-skynet/go-bert.cpp (#463)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-06-01 16:21:13 +02:00
Aisuko
c8a4a4f4e9
feat: Add new test cases for LoadConfigs (#447)
Signed-off-by: Aisuko <urakiny@gmail.com>
2023-06-01 16:20:45 +02:00
ci-robbot [bot]
275c124701
⬆️ Update go-skynet/go-llama.cpp (#458)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-31 22:59:02 +02:00
ci-robbot [bot]
87a6bbd251
⬆️ Update ggerganov/whisper.cpp (#462)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-31 22:58:44 +02:00
ci-robbot [bot]
5623a7c331
⬆️ Update go-skynet/go-bert.cpp (#418)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-31 00:45:07 +02:00
ci-robbot [bot]
9e3ca6d1a3
⬆️ Update nomic-ai/gpt4all (#422)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-31 00:44:52 +02:00
ci-robbot [bot]
fa58965bbc
⬆️ Update ggerganov/whisper.cpp (#419)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-30 23:04:53 +02:00
ci-robbot [bot]
f711d35377
⬆️ Update go-skynet/go-ggml-transformers.cpp (#442)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-30 23:04:10 +02:00
ci-robbot [bot]
abd3c62194
⬆️ Update go-skynet/go-llama.cpp (#443)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-30 23:03:48 +02:00
Aisuko
49ce24984c
feat: Add more test-cases and remove dev container (#433)
Signed-off-by: Aisuko <urakiny@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2023-05-30 13:01:55 +02:00