ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-22 14:02:24 +00:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity
2,064 Commits 44 Branches 108 Tags 47 MiB
f579954c83
Commit Graph

2064 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
aae7ad9d73
feat(llama.cpp): guess model defaults from file (#2522) 
* wip: guess informations from gguf file

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* update go mod

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Identify llama3

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Do not try to guess the name, as reading gguf files can be expensive

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Allow to disable guessing

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-08 22:13:02 +02:00
LocalAI [bot]
23b3d22525
⬆️ Update ggerganov/llama.cpp (#2518) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-07 23:35:16 +00:00
Ettore Di Giacinto
603d81dda1
feat(install): add install.sh for quick installs (#2489) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 22:30:41 +02:00
LocalAI [bot]
a21a52d384
models(gallery): ⬆️ update checksum (#2519) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-07 22:17:25 +02:00
Dave
219078a5e0
test: e2e /reranker endpoint (#2211) 
Create a simple e2e test for the /reranker api \\ go mod tidy

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-07 18:45:52 +00:00
Ettore Di Giacinto
3b7a78adda
fix(stream): do not break channel consumption (#2517) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 17:20:42 +02:00
Sertaç Özercan
0d62594099
fix: fix chat webui response parsing (#2515) 
fix: fix chat webui

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-06-07 17:20:31 +02:00
Dave
d38e9090df
experiment: -j4 for build-linux: (#2514) 
experiment: set -j4 to see if things go faster, while we wait for a proper fix from mudler

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-07 11:22:28 +02:00
Ettore Di Giacinto
b049805c9b
ci: run release build on self-hosted runners (#2505) 2024-06-06 22:16:34 -04:00
LocalAI [bot]
0f9b58f2cf
⬆️ Update ggerganov/llama.cpp (#2508) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 23:48:17 +00:00
LocalAI [bot]
0f134d557e
⬆️ Update ggerganov/whisper.cpp (#2507) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 23:21:25 +00:00
Ettore Di Giacinto
2676e127ae
models(gallery): add llama3-8b-feifei-1.0-iq-imatrix (#2511) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:17:59 +02:00
Ettore Di Giacinto
270d4f8413
models(gallery): add rawr_llama3_8b-iq-imatrix (#2510) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:12:11 +02:00
Ettore Di Giacinto
2d79cee8cb
models(gallery): add llama3-8B-aifeifei-1.0-iq-imatrix (#2509) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:07:20 +02:00
Ettore Di Giacinto
4c9623f50d
deps(whisper): update, add libcufft-dev (#2501) 
* arrow_up: Update ggerganov/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(build): add libcufft-dev

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 08:41:04 +02:00
Ettore Di Giacinto
596cf76135
build(intel): bundle intel variants in single-binary (#2494) 
* wip: try to build also intel variants

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add dependencies

* Select automatically intel backend

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-06 08:40:51 +02:00
LocalAI [bot]
a293aa1b79
⬆️ Update ggerganov/llama.cpp (#2493) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 00:02:51 +00:00
Ettore Di Giacinto
c4eb02c80f
models(gallery): add l3-8b-stheno-v3.2-iq-imatrix (#2500) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:46:59 +02:00
Ettore Di Giacinto
9c9198ff08
models(gallery): add Llama-3-Yggdrasil-2.0-8B (#2499) 
models(gallery): add Llama-3-Yggdrasil-2.0-8B-GGUF

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:42:23 +02:00
Ettore Di Giacinto
83c79d5453
models(gallery): add llama-3-instruct-8b-SimPO-ExPO (#2498) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:37:59 +02:00
Ettore Di Giacinto
88fd000065
models(gallery): add phi-3-4x4b (#2497) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:29:15 +02:00
Ettore Di Giacinto
956d652314
models(gallery): add nyun (#2496) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:22:58 +02:00
Ettore Di Giacinto
9ce2b4d71f
models(gallery): add dolphin-2.9.2-phi-3-Medium-abliterated (#2495) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:14:43 +02:00
Ettore Di Giacinto
4e974cb4fc
models(gallery): add dolphin-2.9.2-Phi-3-Medium (#2492) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 19:17:20 +02:00
Dave
d072835796
feat:OpaqueErrors to hide error information (#2486) 
* adds a new configuration option to hide all error message information from http requests
---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-05 08:45:24 +02:00
Ettore Di Giacinto
17cf6c4a4d
feat(amdgpu): try to build in single binary (#2485) 
* feat(amdgpu): try to build in single binary

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Release space from worker

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 08:44:15 +02:00
LocalAI [bot]
fab3e711ff
⬆️ Update ggerganov/llama.cpp (#2487) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-04 23:11:28 +00:00
Dave
4e1463fec2
feat: fiber CSRF (#2482) 
new config option - enables or disables the fiber csrf middleware

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 19:43:46 +00:00
Dave
2fc6fe806b
fix: pkg/downloader should respect basePath for file:// urls (#2481) 
* pass basePath down to pkg/downloader

Signed-off-by: Dave Lee <dave@gray101.com>

* enforce

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 14:32:47 +00:00
Ettore Di Giacinto
bdd6769b2d
feat(default): use number of physical cores as default (#2483) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-04 15:23:29 +02:00
Ettore Di Giacinto
1ffee9989f
README: update sponsors list (#2476) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-04 15:23:00 +02:00
Dave
34ab442ce9
toil: bump grpc version (#2480) 
bump the grpc package version

---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 08:39:19 +02:00
LocalAI [bot]
67aa31faad
⬆️ Update ggerganov/llama.cpp (#2477) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-03 23:09:24 +00:00
fakezeta
6ef78ef7f6
bugfix: CUDA acceleration not working (#2475) 
* bugfix: CUDA acceleration not working

CUDA not working after #2286.
Refactored the code to be more polish

* Update requirements.txt

Missing imports

Signed-off-by: fakezeta <fakezeta@gmail.com>

* Update requirements.txt

Signed-off-by: fakezeta <fakezeta@gmail.com>

---------

Signed-off-by: fakezeta <fakezeta@gmail.com>
 2024-06-03 22:41:42 +02:00
Ettore Di Giacinto
daa7544d9c
Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-03 19:55:01 +02:00
Ettore Di Giacinto
34527737bb
feat(webui): enhance card visibility (#2473) 
Do not let the description text to clutter, also highlight the model
names

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-03 17:07:26 +02:00
Ettore Di Giacinto
148adebe16
docs: fix p2p commands (#2472) 
Also change icons on GPT vision page

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-03 16:58:53 +02:00
Ettore Di Giacinto
bae2a649fd
models(gallery): add new poppy porpoise versions (#2471) 
models(gallery): add new poppy purpoise versions

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-03 15:44:52 +02:00
Ettore Di Giacinto
90945ebab3
models(gallery): add fimbulvetr iqmatrix version (#2470) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-03 15:44:27 +02:00
fakezeta
4a239a4bff
feat(transformers): various enhancements to the transformers backend (#2468) 
update transformers

*Handle Temperature = 0 as greedy search
*Handle custom works as stop words
*Implement KV cache
*Phi 3 no more requires trust_remote_code: true
 2024-06-03 08:52:55 +02:00
LocalAI [bot]
5ddaa19914
⬆️ Update ggerganov/llama.cpp (#2467) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-02 21:34:29 +00:00
Ettore Di Giacinto
77d752a481
fix(gemma): correctly format the template 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-02 10:51:58 +02:00
Ettore Di Giacinto
29ff51c12a
Update gemma stopwords 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-02 01:26:41 +02:00
Ettore Di Giacinto
c0744899c9
models(gallery): add gemma-2b (#2466) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-02 01:15:06 +02:00
LocalAI [bot]
c9092ad39c
models(gallery): ⬆️ update checksum (#2463) 
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-01 23:13:02 +00:00
LocalAI [bot]
b588cae70e
⬆️ Update ggerganov/llama.cpp (#2465) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-01 22:31:32 +00:00
LocalAI [bot]
fb0f188c93
feat(swagger): update swagger (#2464) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-01 22:04:01 +00:00
Chakib Benziane
b99182c8d4
TTS API improvements (#2308) 
* update doc on COQUI_LANGUAGE env variable

Signed-off-by: blob42 <contact@blob42.xyz>

* return errors from tts gRPC backend

Signed-off-by: blob42 <contact@blob42.xyz>

* handle speaker_id and language in coqui TTS backend

Signed-off-by: blob42 <contact@blob42.xyz>

* TTS endpoint: add optional language paramter

Signed-off-by: blob42 <contact@blob42.xyz>

* tts fix: empty language string breaks non-multilingual models

Signed-off-by: blob42 <contact@blob42.xyz>

* allow tts param definition in config file

- consolidate TTS options under `tts` config entry

Signed-off-by: blob42 <contact@blob42.xyz>

* tts: update doc

Signed-off-by: blob42 <contact@blob42.xyz>

---------

Signed-off-by: blob42 <contact@blob42.xyz>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-01 18:26:27 +00:00
Ettore Di Giacinto
95c65d67f5
models(gallery): add all whisper variants (#2462) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-01 20:04:03 +02:00
Ettore Di Giacinto
c603b95ac7
ci: pin build-time protoc (#2461) 
ci: pin protoc

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-01 18:59:15 +02:00