dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 02:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21
3539 commits 62 branches 113 tags 38 MiB
Commit graph

3539 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ettore Di Giacinto
cabe0f4993
chore(model gallery): add davidbrowne17_llamathink-8b-instruct (#4833) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-15 17:31:46 +01:00
Ettore Di Giacinto
1977c7f190
chore(model gallery): add pygmalionai_eleusis-12b (#4832) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-15 17:21:30 +01:00
Ettore Di Giacinto
061e7c4eae
chore(model gallery): add rombo-org_rombo-llm-v3.0-qwen-32b (#4830) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-15 10:58:27 +01:00
LocalAI [bot]
5313e660f6
chore: ⬆️ Update ggerganov/llama.cpp to 300907b2110cc17b4337334dc397e05de2d8f5e0 (#4829) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-14 21:51:49 +00:00
Ettore Di Giacinto
9e32fda304
fix(llama.cpp): improve context shift handling (#4820) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-14 14:55:03 +01:00
Ettore Di Giacinto
83202cae54
chore(model gallery): add nousresearch_deephermes-3-llama-3-8b-preview (#4828) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-14 12:25:00 +01:00
Ettore Di Giacinto
d96addfa9d
chore(model gallery): add open-thoughts_openthinker-32b (#4827) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-14 12:03:46 +01:00
Ettore Di Giacinto
a715fe588d
chore(model gallery): add sicariussicariistuff_phi-lthy4 (#4826) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-14 11:57:14 +01:00
LocalAI [bot]
2ac4a86bb4
chore: ⬆️ Update ggerganov/llama.cpp to 8a8c4ceb6050bd9392609114ca56ae6d26f5b8f5 (#4825) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-13 21:49:57 +00:00
Ettore Di Giacinto
8670d480a6
chore(model gallery): add nvidia_aceinstruct-72b (#4822) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-13 09:58:34 +01:00
Ettore Di Giacinto
af0b4ff237
chore(ci): update labels 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-02-13 09:58:19 +01:00
Ettore Di Giacinto
e694764065
chore(model gallery): add nvidia_aceinstruct-7b (#4821) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-13 09:44:53 +01:00
Ettore Di Giacinto
f3c27e0381
chore(model gallery): add nvidia_aceinstruct-1.5b (#4819) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-13 09:33:40 +01:00
LocalAI [bot]
bf44319d0d
chore: ⬆️ Update ggerganov/llama.cpp to 0fb77f821f6e70ad8b8247a97d1022f0fef78991 (#4814) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-12 22:41:53 +00:00
Ettore Di Giacinto
5b133a640b
chore(model gallery): add theskullery_l3.3-exp-unnamed-model-70b-v0.5 (#4813) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-12 11:05:51 +01:00
Ettore Di Giacinto
0030a3fe75
chore(model gallery): add simplescaling_s1.1-32b (#4812) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-12 11:03:05 +01:00
Ettore Di Giacinto
0a748b009e chore(ci): avoit cache hits until the ci gRPC job is fixed 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-12 09:11:40 +01:00
LocalAI [bot]
257e951def
chore: ⬆️ Update ggerganov/llama.cpp to 90e4dba461b07e635fd1daf3b491c978c7dd0013 (#4810) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-12 00:13:28 +01:00
LocalAI [bot]
fbd82a2dd0
feat(swagger): update swagger (#4809) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-11 21:54:40 +00:00
Ettore Di Giacinto
5db321dad2 chore(ci): do not always regenerate the cache 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-11 16:36:00 +01:00
Ettore Di Giacinto
f5638a6354
feat(diffusers): allow to override image gen options (#4807) 
Use the options field in the model to override kwargs if needed.

This allows to specify from the model yaml config:

```yaml

options:
- foo:bar

```

And each option will be used directly when calling the diffusers
pipeline, e.g:

```python
pipe(
  foo="bar",
)
```

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-11 10:16:32 +01:00
Ettore Di Giacinto
5f64cc6328
Revert "chore(deps): Bump docs/themes/lotusdocs from f5785a2 to 975da91" (#4808) 
Revert "chore(deps): Bump docs/themes/lotusdocs from `f5785a2` to `975da91` (…"

This reverts commit e57b750ca3.
 2025-02-11 10:05:57 +01:00
Ettore Di Giacinto
28b10e8804
chore(swagger): update (#4805) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-11 09:51:01 +01:00
Ettore Di Giacinto
3277f5095d
chore(model gallery): add agentica-org_deepscaler-1.5b-preview (#4804) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-11 09:47:19 +01:00
Ettore Di Giacinto
fe3ced2919 chore(ci): try again to bump parallelism in grpc jobs 
As we moved these out to self-hosted

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-11 09:31:00 +01:00
LocalAI [bot]
45e37a07bb
chore: ⬆️ Update ggerganov/llama.cpp to 19b392d58dc08c366d0b29bd3b9c6991fa4e1662 (#4803) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-11 09:17:02 +01:00
dependabot[bot]
e57b750ca3
chore(deps): Bump docs/themes/lotusdocs from f5785a2 to 975da91 (#4801) 
Bumps [docs/themes/lotusdocs](https://github.com/colinwilson/lotusdocs) from `f5785a2` to `975da91`.
- [Release notes](https://github.com/colinwilson/lotusdocs/releases)
- [Commits](f5785a2399...975da91e83)

---
updated-dependencies:
- dependency-name: docs/themes/lotusdocs
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-02-10 22:27:14 +00:00
Ettore Di Giacinto
49df492268 chore(ci): run grpc build on self-hosted 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 19:44:50 +01:00
Ettore Di Giacinto
516cd660f1
chore(grpcio): reduce parallelism (#4799) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 18:56:13 +01:00
Ettore Di Giacinto
8fd3ace9a1
chore(grpcio): bump to 1.70 (#4798) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 18:38:53 +01:00
Ettore Di Giacinto
099469cb05
chore(tests): decrease parallelism for gRPC builds (#4797) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 12:59:59 +01:00
Ettore Di Giacinto
6be8c0c618
chore(model gallery): add localai-functioncall-qwen2.5-7b-v0.5 (#4796) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 12:07:35 +01:00
Dave
3cddf24747
feat: Centralized Request Processing middleware (#3847) 
* squash past, centralize request middleware PR

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

* migrate bruno request files to examples repo

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

* fix

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

* Update tests/e2e-aio/e2e_test.go

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

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-02-10 12:06:16 +01:00
Ettore Di Giacinto
c330360785
chore(model gallery): add ilsp_llama-krikri-8b-instruct (#4795) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-10 09:54:54 +01:00
LocalAI [bot]
8cd51570e5
chore: ⬆️ Update ggerganov/llama.cpp to 19d3c8293b1f61acbe2dab1d49a17950fd788a4a (#4793) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-09 22:12:01 +00:00
Ettore Di Giacinto
0e7aa5cd15
chore(model gallery): add subtleone_qwen2.5-32b-erudite-writer (#4792) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-09 10:59:46 +01:00
Ettore Di Giacinto
e06a5f49de
chore(model gallery): add huihui-ai_deepseek-r1-distill-llama-70b-abliterated (#4790) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-09 10:53:48 +01:00
Dave
fb2f847507
chore: migrate bruno request files to examples repo (#4788) 
migrate bruno request files to examples repo

Signed-off-by: Dave Lee <dave@gray101.com>
 2025-02-09 10:52:28 +01:00
LocalAI [bot]
e01acc88c9
chore: ⬆️ Update ggerganov/llama.cpp to e6e658319952f7ad269dc11275b9edddc721fc6d (#4787) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-08 21:57:40 +00:00
LocalAI [bot]
7a5912908a
chore: ⬆️ Update ggerganov/llama.cpp to d2fe216fb2fb7ca8627618c9ea3a2e7886325780 (#4780) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-08 09:44:34 +01:00
Ettore Di Giacinto
4b1b942a7f
chore(model gallery): add sicariussicariistuff_redemption_wind_24b (#4781) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-08 09:04:18 +01:00
Ettore Di Giacinto
230fe0098f
chore(model gallery): add cognitivecomputations_dolphin3.0-mistral-24b (#4779) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-07 13:33:24 +01:00
Ettore Di Giacinto
cc163429dc
chore(model gallery): add cognitivecomputations_dolphin3.0-r1-mistral-24b (#4778) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-07 13:31:49 +01:00
Ettore Di Giacinto
f670e0a91c
chore(model gallery): add nohobby_l3.3-prikol-70b-v0.5 (#4777) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-07 13:29:53 +01:00
LocalAI [bot]
731674eee7
chore: ⬆️ Update ggerganov/llama.cpp to 8a59053f63fffc24e730cd3ea067760abfe4a919 (#4776) 
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-02-06 22:02:00 +00:00
Ettore Di Giacinto
cc1f6f913f
fix(llama.cpp): disable mirostat as default (#2911) 
Even if increasing the quality of the output, it has shown to have
performance drawbacks to be so noticeable that the confuses users about
speed of LocalAI ( see also
https://github.com/mudler/LocalAI/issues/2780 ).

This changeset disables Mirostat by default (which can
be still enabled manually).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
 2025-02-06 19:39:59 +01:00
Ettore Di Giacinto
7f90ff7aec
chore(llama-ggml): drop deprecated backend (#4775) 
The GGML format is now dead, since in the next version of LocalAI we
already bring many breaking compatibility changes, taking the occasion
also to drop ggml support (pre-gguf).

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-06 18:36:23 +01:00
Ettore Di Giacinto
8d45670e41
fix(openai): consistently return stop reason (#4771) 
We were not returning a stop reason when no tool was actually called
(even if specified).

Fixes: https://github.com/mudler/LocalAI/issues/4716

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-06 12:41:08 +01:00
Ettore Di Giacinto
e4b8ddb6a1
chore(model gallery): add black-ink-guild_pernicious_prophecy_70b (#4774) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-06 12:03:59 +01:00
Ettore Di Giacinto
a801561f81
chore(model gallery): add tiger-lab_qwen2.5-32b-instruct-cft (#4773) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-02-06 12:01:56 +01:00