ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-21 05:33:09 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity
1,736 Commits 43 Branches 108 Tags 46 MiB
10430a00bd
Commit Graph

1736 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
10430a00bd
feat(hipblas): extend default hipblas GPU_TARGETS (#2426) 
Makefile: extend default hipblas GPU_TARGETS

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-27 22:35:11 +02:00
Ettore Di Giacinto
9f5c274321
feat(images): do not install python deps in the core image (#2425) 
do not install python deps in the core image

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-27 22:07:48 +02:00
Ettore Di Giacinto
d075dc44dd
ci: push test images when building PRs (#2424) 
ci: try to push image

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-27 22:07:35 +02:00
Ettore Di Giacinto
be8ffbdfcf
ci(grpc-cache): also arm64 (#2423) 
grpc-cache: also arm64

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-27 17:23:34 +02:00
Ettore Di Giacinto
eaf653f3d3
models(gallery): add iterative-dpo, fix minicpm (#2422) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-27 17:17:04 +02:00
LocalAI [bot]
e9c28a1ed7
⬆️ Update ggerganov/llama.cpp (#2419) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-26 21:32:05 +00:00
cryptk
ba984c7097
fix: pin version of setuptools for intel builds to work around #2406 (#2414) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-05-26 18:27:07 +00:00
Ettore Di Giacinto
ff1f9125ed
models(gallery): add stheno-mahou (#2418) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 20:12:40 +02:00
Ettore Di Giacinto
2c82058548
models(gallery): add cream-phi-13b (#2417) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 20:11:57 +02:00
cryptk
16433d2e8e
fix: install pytorch from proper index for hipblas builds (#2413) 
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
 2024-05-26 18:05:52 +00:00
Ettore Di Giacinto
345047ed7c
models(gallery): add alpha centauri (#2416) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 20:04:26 +02:00
Ettore Di Giacinto
6343758f9c
models(gallery): add poppy porpoise 0.85 (#2415) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 19:59:49 +02:00
Ettore Di Giacinto
135208806c
models(gallery): add minicpm (#2412) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 15:58:19 +02:00
Ettore Di Giacinto
3280de7adf
models(gallery): add Mahou (#2411) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 15:43:31 +02:00
Ettore Di Giacinto
db3113c5c8
fix(watcher): do not emit fatal errors (#2410) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-26 14:48:30 +02:00
LocalAI [bot]
593fb62bf0
⬆️ Update ggerganov/llama.cpp (#2409) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-26 08:43:50 +00:00
LocalAI [bot]
480834f75b
⬆️ Update ggerganov/whisper.cpp (#2408) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-26 08:05:15 +00:00
Sertaç Özercan
3200a6655e
fix: gpu fetch device info (#2403) 
* fix: gpu fetch device info

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* use pciutils package

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

---------

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-05-26 09:56:06 +02:00
Ettore Di Giacinto
b90cdced59 docs: rewording 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-25 20:18:25 +02:00
Ettore Di Giacinto
fc3502b56f docs: rewording 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-25 20:17:04 +02:00
Ettore Di Giacinto
785adc1ed5 docs: updaet title 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-25 16:13:48 +02:00
Ettore Di Giacinto
e25fc656c9
Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-05-25 16:13:04 +02:00
Ettore Di Giacinto
bb3ec56de3 docs: add distributed inferencing docs 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-25 16:12:08 +02:00
Ettore Di Giacinto
785c54e7b0
models(gallery): add Mirai Nova (#2405) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-25 16:11:01 +02:00
Ettore Di Giacinto
003b43f6fc
Update quickstart.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-05-25 10:18:20 +02:00
LocalAI [bot]
663488b6bd
⬆️ Update docs version mudler/LocalAI (#2398) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-25 10:08:35 +02:00
Ettore Di Giacinto
e1d6b706f4
Update quickstart.md (#2404) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-05-25 10:08:23 +02:00
Sertaç Özercan
29615576fb
ci: fix sd release (#2400) 
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-05-25 09:33:50 +02:00
LocalAI [bot]
f8cea16c03
⬆️ Update ggerganov/llama.cpp (#2399) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-24 21:52:13 +00:00
Ettore Di Giacinto
e0187c2a1a ci: do not tag latest on AIO automatically 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-24 09:41:13 +02:00
Ettore Di Giacinto
b76d2fe68a
Update quickstart.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-05-24 09:02:59 +02:00
Ettore Di Giacinto
ee4f722bf8
models(gallery): add aya-35b (#2391) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-23 23:51:34 +02:00
LocalAI [bot]
dce63237f2
⬆️ Update ggerganov/llama.cpp (#2360) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-23 21:02:13 +00:00
Dave
0b637465d9
refactor: Minor improvements to BackendConfigLoader (#2353) 
some minor renames and refactorings within BackendConfigLoader - make things more consistent, remove underused code, rename things for clarity

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-05-23 22:48:12 +02:00
Mauro Morales
114f549f5e
Add warning for running the binary on MacOS (#2389) 2024-05-23 22:40:55 +02:00
Ettore Di Giacinto
ea330d452d
models(gallery): add mistral-0.3 and command-r, update functions (#2388) 
* models(gallery): add mistral-0.3 and command-r, update functions

Add also disable_parallel_new_lines to disable newlines in the JSON
output when forcing parallel tools. Some models (like mistral) might be
very sensible to that when being used for function calling.

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

* models(gallery): add aya-23-8b

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-23 19:16:08 +02:00
Valentin Fröhlich
eb11a46a73
Add Home Assistant Integration (#2387) 
Add https://github.com/valentinfrlch/ha-gpt4vision to Home Assistant Integration section

gpt4vision uses LocalAI's API to send images along with a prompt and return the models output.

Signed-off-by: Valentin Fröhlich <85313672+valentinfrlch@users.noreply.github.com>
 2024-05-23 15:21:01 +02:00
LocalAI [bot]
b57e14d65c
models(gallery): ⬆️ update checksum (#2386) 
⬆️ 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>
 2024-05-23 08:42:45 +02:00
Sertaç Özercan
7efa8e75d4
fix: stablediffusion binary (#2385) 
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-05-23 08:34:37 +02:00
Ettore Di Giacinto
7551369abe
Update checksum_checker.sh 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-05-23 08:33:58 +02:00
LocalAI [bot]
79915bcd11
models(gallery): ⬆️ update checksum (#2383) 
⬆️ 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>
 2024-05-23 01:10:15 +00:00
LocalAI [bot]
c8d7d14a37
⬆️ Update go-skynet/go-bert.cpp (#1225) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-22 23:42:38 +00:00
LocalAI [bot]
c56bc0de98
⬆️ Update ggerganov/whisper.cpp (#2361) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-05-23 01:02:57 +02:00
Ettore Di Giacinto
3a9408363b
deps(llama.cpp): update and adapt API changes (#2381) 
deps(llama.cpp): update and rename function

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-23 01:02:11 +02:00
Ettore Di Giacinto
21a12c2cdd
ci(checksum_checker): do get sha from hf API when available (#2380) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 23:51:02 +02:00
Ettore Di Giacinto
371d0cc1f7
ci: generate specific image for intel builds (#2374) 
ci: fix intel images until are fixed upstream

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 23:35:39 +02:00
Ettore Di Giacinto
23fa92bec0
models(gallery): add hercules and helpingAI (#2376) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 22:42:41 +02:00
Ettore Di Giacinto
f91e4e5c03
ci: correctly build p2p in GO_TAGS (#2369) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 10:15:36 +02:00
Ettore Di Giacinto
6cbe6a4f99
models(gallery): add phi-3-medium-4k-instruct (#2367) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 08:32:30 +02:00
Ettore Di Giacinto
491e1d752b
feat(functions): relax mixedgrammars (#2365) 
* feat(functions): relax mixedgrammars

Extend even more the functionalities and when mixed mode is enabled,
tolerate also both strings and JSON in the result - in this case we make
sure that the JSON can be correctly parsed.

This also updates the examples and the gallery model to configure the
grammar.

The changeset also breaks current function/grammar configuration as it
reserves now a stanza in the YAML config.

For example:

```yaml
function:
  grammar:
    # This allows the grammar to also return messages
    mixed_mode: true
    # Suffix to add to the grammar
    # prefix: '<tool_call>\n'
    # Force parallel calls in the grammar
    # parallel_calls: true
```

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

* refactor, add a way to disable mixed json and freestring

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

* Fix linting issues

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-05-22 00:14:16 +02:00