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
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
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
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
2e61ff32ad
ci: add cuda builds to release ( #1702 )
...
Signed-off-by: Sertac Ozercan <sozercan@gmail.com >
2024-02-13 08:35:39 +00:00
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
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
6e0eb96c61
fix: drop unused code ( #1697 )
...
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-02-11 11:28:59 +01:00
fd68bf7084
fix(vall-e-x): Fix voice cloning ( #1696 )
2024-02-11 11:20:00 +01:00
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
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
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
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
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
3875e5e0e5
Update README.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-02-09 00:03:07 +01:00
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
f1f6035967
Update README.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-02-08 20:39:00 +01:00
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
d0a6a35b55
Update README.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-02-07 09:40:31 +01:00
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
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
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
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
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
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
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
ea7b33b0d2
Update integrations.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-02-05 15:59:31 +01:00
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
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
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
f083a901fe
Fix HTTP links in README.md ( #1677 )
...
Signed-off-by: Nicolas Vermande <vfiftyfive@gmail.com >
2024-02-04 00:54:49 +01:00
df13ba655c
Drop old falcon backend (deprecated) ( #1675 )
...
Drop old falcon backend
2024-02-03 13:01:13 +01:00
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
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
3c24a70a1b
fix (docs): fixed broken links github/ -> github.com/ ( #1672 )
...
fix broken links
2024-02-02 18:18:03 +01:00
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
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
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
555bc02665
Update codellama-7b.yaml
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-30 11:36:20 +01:00
c1bae1ee81
⬆️ Update ggerganov/llama.cpp ( #1656 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-30 00:43:36 +01:00
f2ed3df3da
⬆️ Update docs version mudler/LocalAI ( #1661 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-30 00:43:18 +01:00
abd678e147
⬆️ Update ggerganov/llama.cpp ( #1655 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-28 09:24:44 +01:00
6ac5d814fb
feat(startup): fetch model definition remotely ( #1654 )
2024-01-28 00:14:16 +01:00
f928899338
⬆️ Update ggerganov/llama.cpp ( #1652 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-27 00:13:38 +01:00
5a6fd98839
fix(paths): automatically create paths ( #1650 )
...
Especially useful when running inside a container.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-01-27 00:13:19 +01:00
072f71dfb7
Update codellama-7b.yaml
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-26 18:35:33 +01:00
670cee8274
Update transformers-tinyllama.yaml
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-26 18:29:38 +01:00
9f1be45552
Update quickstart.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-26 17:55:20 +01:00
f1846ae5ac
Update phi-2.yaml
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-26 16:22:54 +01:00
ac19998e5e
⬆️ Update ggerganov/llama.cpp ( #1644 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-26 00:13:39 +01:00
