Commit Graph

1192 Commits

Author SHA1 Message Date
Chakib Benziane
594eb468df
Add TTS dependency for cuda based builds fixes #1727 (#1730)
Signed-off-by: Chakib Benziane <contact@blob42.xyz>
2024-02-20 21:59:43 +01:00
Ettore Di Giacinto
960d314e4f
feat(tools): Parallel function calling (#1726)
feat(tools): support returning multiple tools choices

Fixes: https://github.com/mudler/LocalAI/issues/1275
2024-02-20 21:58:45 +01:00
Ettore Di Giacinto
ed3b50622b
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-20 19:55:36 +01:00
Ettore Di Giacinto
9f2235c208
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-19 19:49:00 +01:00
Ettore Di Giacinto
4ec50bfc41
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-19 19:03:09 +01:00
Ettore Di Giacinto
51b67a247a
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-18 13:37:16 +01:00
Steven Christou
01205fd4c0
Initial implementation of upload files api. (#1703)
* Initial implementation of upload files api.

* Move sanitize method to utils.

* Save uploaded data to uploads folder.

* Avoid loop if we do not have a purpose.

* Minor cleanup of api and fix bug where deleting duplicate filename cause error.

* Revert defer of saving config

* Moved creation of directory to startup.

* Make file names unique when storing on disk.

* Add test for files api.

* Update dependencies.
2024-02-18 10:12:02 +00:00
Ettore Di Giacinto
c72808f18b
feat(tools): support Tool calls in the API (#1715)
* feat(tools): support Tools in the API

Co-authored-by: =?UTF-8?q?Stephan=20A=C3=9Fmus?= <stephan.assmus@sap.com>

* feat(tools): support function streaming

* Adhere to new return types when using tools instead of functions

* Keep backward compatibility with function calling

* Evaluate function names in chat templates

* Disable recovery with --debug

* Correctly stream out the entire result

* Detect when llm chooses to reply and to not perform any action in SSE

* Feedback from code review

---------

Co-authored-by: =?UTF-8?q?Stephan=20A=C3=9Fmus?= <stephan.assmus@sap.com>
2024-02-17 10:00:34 +01:00
Ettore Di Giacinto
6b539a2972
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-16 15:22:35 +01:00
LocalAI [bot]
2151d21862
⬆️ Update docs version mudler/LocalAI (#1718)
* ⬆️ Update docs version mudler/LocalAI

Signed-off-by: GitHub <noreply@github.com>

* Update docs/data/version.json

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: GitHub <noreply@github.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-16 15:11:53 +01:00
fenfir
fb0a4c5d9a
Build docker container for ROCm (#1595)
* Dockerfile changes to build for ROCm

* Adjust linker flags for ROCm

* Update conda env for diffusers and transformers to use ROCm pytorch

* Update transformers conda env for ROCm

* ci: build hipblas images

* fixup rebase

* use self-hosted

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

* specify LD_LIBRARY_PATH only when BUILD_TYPE=hipblas

---------

Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: mudler <mudler@localai.io>
2024-02-16 15:08:50 +01:00
Ettore Di Giacinto
e690bf387a
fix(tts): fix regression when supplying backend from requests (#1713)
fixes #1707

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-15 17:33:06 +01:00
Ettore Di Giacinto
5e155fb081
fix(python): pin exllama2 (#1711)
fix(python): pin python deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-14 21:44:12 +01:00
Ettore Di Giacinto
39a6b562cf
fix(llama.cpp): downgrade to a known working version (#1706)
sycl support is broken otherwise.

See upstream issue: https://github.com/ggerganov/llama.cpp/issues/5469

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-14 10:28:06 +01:00
Ettore Di Giacinto
c56b6ddb1c
fix(llama.cpp): disable infinite context shifting (#1704)
Infinite context loop might as well trigger an infinite loop of context
shifting if the model hallucinates and does not stop answering.
This has the unpleasant effect that the predicion never terminates,
which is the case especially on small models which tends to hallucinate.

Workarounds https://github.com/mudler/LocalAI/issues/1333 by removing
context-shifting.

See also upstream issue: https://github.com/ggerganov/llama.cpp/issues/3969
2024-02-13 21:17:21 +01:00
Sertaç Özercan
2e61ff32ad
ci: add cuda builds to release (#1702)
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
2024-02-13 08:35:39 +00:00
LocalAI [bot]
02f6e18adc
⬆️ Update ggerganov/llama.cpp (#1700)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-12 21:43:33 +00:00
LocalAI [bot]
4436e62cf1
⬆️ Update ggerganov/llama.cpp (#1698)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-12 09:56:04 +01:00
Ettore Di Giacinto
6e0eb96c61
fix: drop unused code (#1697)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-11 11:28:59 +01:00
Ettore Di Giacinto
fd68bf7084
fix(vall-e-x): Fix voice cloning (#1696) 2024-02-11 11:20:00 +01:00
LocalAI [bot]
58cdf97361
⬆️ Update ggerganov/llama.cpp (#1694)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-11 10:01:11 +01:00
Ettore Di Giacinto
53dbe36f32
feat(tts): respect YAMLs config file, add sycl docs/examples (#1692)
* feat(refactor): refactor config and input reading

* feat(tts): read config file for TTS

* examples(kubernetes): Add simple deployment example

* examples(kubernetes): Add simple deployment for intel arc

* docs(sycl): add sycl example

* feat(tts): do not always pick a first model

* fixups to run vall-e-x on container

* Correctly resolve backend
2024-02-10 21:37:03 +01:00
LocalAI [bot]
081bd07fd1
⬆️ Update docs version mudler/LocalAI (#1693)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-10 21:33:14 +01:00
LocalAI [bot]
ef1306f703
⬆️ Update mudler/go-stable-diffusion (#1674)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-09 21:59:15 +00:00
LocalAI [bot]
3196967995
⬆️ Update ggerganov/llama.cpp (#1691)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-09 21:50:34 +00:00
Ettore Di Giacinto
3875e5e0e5
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-09 00:03:07 +01:00
LocalAI [bot]
fc8423392f
⬆️ Update ggerganov/llama.cpp (#1688)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-09 00:02:23 +01:00
Ettore Di Giacinto
f1f6035967
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-08 20:39:00 +01:00
Ettore Di Giacinto
ddd21f1644
feat: Use ubuntu as base for container images, drop deprecated ggml-transformers backends (#1689)
* cleanup backends

* switch image to ubuntu 22.04

* adapt commands for ubuntu

* transformers cleanup

* no contrib on ubuntu

* Change test model to gguf

* ci: disable bark tests (too cpu-intensive)

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

* cleanup

* refinements

* use intel base image

* Makefile: Add docker targets

* Change test model

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-08 20:12:51 +01:00
Ettore Di Giacinto
d0a6a35b55
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-07 09:40:31 +01:00
Ettore Di Giacinto
e0632f2ce2
fix(llama.cpp): downgrade to fix sycl build
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-07 00:16:52 +01:00
Ettore Di Giacinto
37e6974afe
ci: fix extra(bark) tests
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-06 20:49:28 +01:00
Ettore Di Giacinto
e23e490455
Revert "fix(Dockerfile): sycl dependencies" (#1687)
Revert "fix(Dockerfile): sycl dependencies (#1686)"

This reverts commit f76bb8954b.
2024-02-06 20:48:29 +01:00
Ettore Di Giacinto
f76bb8954b
fix(Dockerfile): sycl dependencies (#1686)
* fix(Dockerfile): sycl dependencies

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

* fix(ci): cleanup before running bark test

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-06 19:42:52 +01:00
Ettore Di Giacinto
d168c7c9dc
ci: cleanup worker before run (#1685)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-06 19:42:27 +01:00
Ettore Di Giacinto
fd9d060c94
ci: fix sycl image suffix
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-06 15:52:21 +01:00
LocalAI [bot]
d8b17795d7
⬆️ Update ggerganov/llama.cpp (#1683)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-06 09:26:01 +01:00
Ettore Di Giacinto
ea7b33b0d2
Update integrations.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-02-05 15:59:31 +01:00
LocalAI [bot]
8ace0a9ba7
⬆️ Update ggerganov/llama.cpp (#1681)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-04 21:59:14 +00:00
Ettore Di Giacinto
98ad93d53e
Drop ggml-based gpt2 and starcoder (supported by llama.cpp) (#1679)
* Drop ggml-based gpt2 and starcoder (supported by llama.cpp)

* Update compatibility table
2024-02-04 13:15:51 +01:00
LocalAI [bot]
38e4ec0b2a
⬆️ Update ggerganov/llama.cpp (#1678)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-04 00:55:12 +01:00
Nicolas Vermande
f083a901fe
Fix HTTP links in README.md (#1677)
Signed-off-by: Nicolas Vermande <vfiftyfive@gmail.com>
2024-02-04 00:54:49 +01:00
Ettore Di Giacinto
df13ba655c
Drop old falcon backend (deprecated) (#1675)
Drop old falcon backend
2024-02-03 13:01:13 +01:00
LocalAI [bot]
7678b25755
⬆️ Update ggerganov/llama.cpp (#1673)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-02 21:46:26 +00:00
LocalAI [bot]
c87ca4f320
⬆️ Update ggerganov/llama.cpp (#1669)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-02-02 19:14:03 +01:00
Ivan Smirnov
3c24a70a1b
fix (docs): fixed broken links github/ -> github.com/ (#1672)
fix broken links
2024-02-02 18:18:03 +01:00
Richard Palethorpe
e46db63e06
feat(mamba): Add bagel-dpo-2.8b (#1671)
Adds the Mamba-slimpj model fine-tuned with bagel.
https://huggingface.co/jondurbin/bagel-dpo-2.8b-v0.2

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2024-02-02 18:17:44 +01:00
Ettore Di Giacinto
1c57f8d077
feat(sycl): Add support for Intel GPUs with sycl (#1647) (#1660)
* feat(sycl): Add sycl support (#1647)

* onekit: install without prompts

* set cmake args only in grpc-server

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

* cleanup

* fixup sycl source env

* Cleanup docs

* ci: runs on self-hosted

* fix typo

* bump llama.cpp

* llama.cpp: update server

* adapt to upstream changes

* adapt to upstream changes

* docs: add sycl

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-02-01 19:21:52 +01:00
LocalAI [bot]
16cebf0390
⬆️ Update ggerganov/llama.cpp (#1665)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2024-01-30 23:38:05 +00:00
Ettore Di Giacinto
555bc02665
Update codellama-7b.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-01-30 11:36:20 +01:00