Commit Graph

  • e63fe09539
    chore(deps): Bump torch in /backend/python/sentencetransformers #4396 dependabot[bot] 2024-12-16 18:14:13 +0000
  • 7ca0e2d925
    fix(python): remove pin to setuptools, pin python version (#4395) Ettore Di Giacinto 2024-12-16 10:55:02 +0100
  • 524a21dd15 fix(setuptools): remove pin #4395 Ettore Di Giacinto 2024-12-16 10:14:28 +0100
  • 037e8030bf
    chore(model gallery): add qwen2-7b-multilingual-rp (#4394) Ettore Di Giacinto 2024-12-16 09:48:33 +0100
  • 472d11f884
    chore(model gallery): add marco-o1-uncensored (#4393) Ettore Di Giacinto 2024-12-16 09:48:23 +0100
  • b40d5d12b7
    chore(model gallery): add naturallm-7b-instruct (#4392) Ettore Di Giacinto 2024-12-16 09:47:49 +0100
  • 8466aa3faa chore(model gallery): add marco-o1-uncensored #4393 Ettore Di Giacinto 2024-12-16 09:44:16 +0100
  • 0195315195 chore(model gallery): add qwen2-7b-multilingual-rp #4394 Ettore Di Giacinto 2024-12-16 09:42:56 +0100
  • ec15bccc84 chore(model gallery): add naturallm-7b-instruct #4392 Ettore Di Giacinto 2024-12-16 09:40:12 +0100
  • 6938618e30
    chore: ⬆️ Update ggerganov/llama.cpp to a0974156f334acf8af5858d7ede5ab7d7490d415 (#4391) LocalAI [bot] 2024-12-15 23:01:44 +0100
  • d434fe59a7 ⬆️ Update ggerganov/llama.cpp #4391 mudler 2024-12-15 20:06:32 +0000
  • 5d9c530eaa
    fix(gallery): disable default embeddings Ettore Di Giacinto 2024-12-15 18:43:39 +0100
  • b93235a17a
    Merge a7f15cada7 into 9429a53db7 #3660 TwinFin 2024-12-15 19:25:02 +0800
  • 9429a53db7
    chore(model gallery): add neumind-math-7b-instruct (#4388) Ettore Di Giacinto 2024-12-15 10:07:56 +0100
  • 1d6d301370
    chore(model gallery): add fusechat-llama-3.1-8b-instruct (#4387) Ettore Di Giacinto 2024-12-15 10:07:42 +0100
  • 8f2be82667
    chore(model gallery): add fusechat-llama-3.2-3b-instruct (#4386) Ettore Di Giacinto 2024-12-15 10:07:30 +0100
  • 774a249619 chore(model gallery): add neumind-math-7b-instruct #4388 Ettore Di Giacinto 2024-12-15 10:04:20 +0100
  • bd41d63542 chore(model gallery): add fusechat-llama-3.1-8b-instruct #4387 Ettore Di Giacinto 2024-12-15 10:03:08 +0100
  • ba4903c346 chore(model gallery): add fusechat-llama-3.2-3b-instruct #4386 Ettore Di Giacinto 2024-12-15 10:01:59 +0100
  • cca911f3e5
    chore: ⬆️ Update ggerganov/llama.cpp to e52aba537a34d51a65cddec6bc6dafc9031edc63 (#4385) LocalAI [bot] 2024-12-15 09:59:20 +0100
  • 0beed9e7d3
    Merge 171c55d7d5 into e37bbbaacc #3477 Dave 2024-12-14 21:49:01 +0100
  • f07582d919
    Merge branch 'master' into update/CPPLLAMA_VERSION #4385 Ettore Di Giacinto 2024-12-14 21:26:21 +0100
  • e37bbbaacc
    fix: correct gallery/index.yaml (#4384) Jason Godsey 2024-12-14 13:25:51 -0700
  • 59cbf38b4b
    fix(gallery): correct syntax typo Ettore Di Giacinto 2024-12-14 21:21:27 +0100
  • 02295f33d1 ⬆️ Update ggerganov/llama.cpp mudler 2024-12-14 20:06:33 +0000
  • 601650c1ca
    Update index.yaml #4384 Jason Godsey 2024-12-14 10:44:11 -0700
  • 432c31d904
    chore(model gallery): add chronos-gold-12b-1.0 (#4381) Ettore Di Giacinto 2024-12-14 11:27:25 +0100
  • af33483687
    chore(model gallery): add fusechat-qwen-2.5-7b-instruct (#4380) Ettore Di Giacinto 2024-12-14 11:27:11 +0100
  • 5051074845
    chore(model gallery): add fusechat-gemma-2-9b-instruct (#4379) Ettore Di Giacinto 2024-12-14 11:26:40 +0100
  • a55da2aa40 chore(model gallery): add fusechat-gemma-2-9b-instruct #4379 Ettore Di Giacinto 2024-12-14 11:25:23 +0100
  • 8d2e00652a chore(model gallery): add fusechat-qwen-2.5-7b-instruct #4380 Ettore Di Giacinto 2024-12-14 11:24:08 +0100
  • 7149f2c78d chore(model gallery): add chronos-gold-12b-1.0 #4381 Ettore Di Giacinto 2024-12-14 11:17:51 +0100
  • fc4a714992
    feat(llama.cpp): bump and adapt to upstream changes (#4378) Ettore Di Giacinto 2024-12-14 00:30:52 +0100
  • b8d9e8666e feat(llama.cpp): bump and adapt to upstream changes #4378 Ettore Di Giacinto 2024-12-13 22:46:17 +0100
  • 493d692bd9 ⬆️ Update ggerganov/llama.cpp #4377 mudler 2024-12-13 20:07:22 +0000
  • 0429e00746
    chore(model gallery): add hermes-3-llama-3.2-3b (#4376) Ettore Di Giacinto 2024-12-13 09:51:26 +0100
  • 73f1f25b9a
    chore(model gallery): add evathene-v1.3 (#4375) Ettore Di Giacinto 2024-12-13 09:51:13 +0100
  • 044570fa85
    chore(model gallery): add l3.3-ms-evayale-70b (#4374) Ettore Di Giacinto 2024-12-13 09:50:41 +0100
  • 80098f28a2 chore(model gallery): add evathene-v1.3 #4375 Ettore Di Giacinto 2024-12-13 09:49:33 +0100
  • fc0804e2e8 chore(model gallery): add hermes-3-llama-3.2-3b #4376 Ettore Di Giacinto 2024-12-13 09:27:49 +0100
  • 230852f481 chore(model gallery): add l3.3-ms-evayale-70b #4374 Ettore Di Giacinto 2024-12-13 09:24:03 +0100
  • 37527420de
    chore: ⬆️ Update ggerganov/llama.cpp to 274ec65af6e54039eb95cb44904af5c945dca1fa (#4372) LocalAI [bot] 2024-12-12 22:44:54 +0100
  • 8e45145a0a ⬆️ Update ggerganov/llama.cpp #4372 mudler 2024-12-12 20:07:30 +0000
  • 1854b8c612
    chore(model gallery): add l3.3-70b-euryale-v2.3 (#4371) Ettore Di Giacinto 2024-12-12 12:22:48 +0100
  • e43f450d78 chore(model gallery): add l3.3-70b-euryale-v2.3 #4371 Ettore Di Giacinto 2024-12-12 12:11:17 +0100
  • b8824f2ad9
    chore(model gallery): add deepthought-8b-llama-v0.01-alpha (#4370) Ettore Di Giacinto 2024-12-12 12:07:57 +0100
  • 3ab83e91df
    chore(model gallery): add 72b-qwen2.5-kunou-v1 (#4369) Ettore Di Giacinto 2024-12-12 12:07:41 +0100
  • 1f523fc0da chore(model gallery): add 72b-qwen2.5-kunou-v1 #4369 Ettore Di Giacinto 2024-12-12 11:41:41 +0100
  • 915da0dca6 chore(model gallery): add deepthought-8b-llama-v0.01-alpha #4370 Ettore Di Giacinto 2024-12-12 10:58:30 +0100
  • f2cb261797
    chore: ⬆️ Update ggerganov/llama.cpp to 235f6e14bf0ed0211c51aeff14139038ae1000aa (#4366) LocalAI [bot] 2024-12-12 09:23:36 +0100
  • 894a30296a feat: unify and propagate CMAKE_ARGS to GGML-based backends #4367 propagate_cmake_args Ettore Di Giacinto 2024-12-11 22:01:05 +0100
  • 6dd6237935 ⬆️ Update ggerganov/llama.cpp #4366 mudler 2024-12-11 20:07:31 +0000
  • c85f46a71d
    chore(model gallery): add sailor2-20b-chat (#4365) Ettore Di Giacinto 2024-12-11 10:55:04 +0100
  • cf173135c1 chore(model gallery): add sailor2-20b-chat #4365 Ettore Di Giacinto 2024-12-11 10:52:07 +0100
  • 75b283d83c
    chore(model gallery): add sailor2-8b-chat (#4364) Ettore Di Giacinto 2024-12-11 10:51:39 +0100
  • 7f6487ee02 chore(model gallery): add sailor2-8b-chat #4364 Ettore Di Giacinto 2024-12-11 10:48:58 +0100
  • 1918efdfdd
    chore(model gallery): add sailor2-1b-chat (#4363) Ettore Di Giacinto 2024-12-11 10:32:18 +0100
  • 606cd477b0 chore(model gallery): add sailor2-1b-chat #4363 Ettore Di Giacinto 2024-12-11 10:11:41 +0100
  • ec239a0cd0
    docs: ⬆️ update docs version mudler/LocalAI (#4359) LocalAI [bot] 2024-12-11 10:04:16 +0100
  • b74a936178
    chore: ⬆️ Update ggerganov/llama.cpp to dafae66cc242eb766797194d3c85c5e502625623 (#4360) LocalAI [bot] 2024-12-10 22:45:42 +0100
  • c9c349e5d3 ⬆️ Update ggerganov/llama.cpp #4360 mudler 2024-12-10 20:07:22 +0000
  • 3a04c37ca0 ⬆️ Update docs version mudler/LocalAI #4359 mudler 2024-12-10 20:04:53 +0000
  • 59cf30a80e
    chore: ⬆️ Update ggerganov/llama.cpp to 26a8406ba9198eb6fdd8329fa717555b4f77f05f (#4358) v2.24.2 release/v2.24.2 Ettore Di Giacinto 2024-12-10 15:51:45 +0100
  • d8df199fad chore: ⬆️ Update ggerganov/llama.cpp to 26a8406ba9198eb6fdd8329fa717555b4f77f05f (#4353) #4358 LocalAI [bot] 2024-12-10 09:10:58 +0100
  • de1ddb8ba6
    chore(model gallery): add b-nimita-l3-8b-v0.02 (#4357) Ettore Di Giacinto 2024-12-10 09:42:47 +0100
  • 272763f625
    chore(model gallery): add intellect-1-instruct (#4356) Ettore Di Giacinto 2024-12-10 09:42:37 +0100
  • 3aff87a5cf
    chore(model gallery): add qwen2.5-math-14b-instruct (#4355) Ettore Di Giacinto 2024-12-10 09:42:24 +0100
  • 2d81931a2e chore(model gallery): add intellect-1-instruct #4356 Ettore Di Giacinto 2024-12-10 09:34:52 +0100
  • 3426ddb0d6 chore(model gallery): add b-nimita-l3-8b-v0.02 #4357 Ettore Di Giacinto 2024-12-10 09:30:26 +0100
  • 8751ac03f5 chore(model gallery): add qwen2.5-math-14b-instruct #4355 Ettore Di Giacinto 2024-12-10 09:29:02 +0100
  • 885118e863
    chore: ⬆️ Update ggerganov/llama.cpp to 26a8406ba9198eb6fdd8329fa717555b4f77f05f (#4353) LocalAI [bot] 2024-12-10 09:10:58 +0100
  • a03a9b9e51
    chore(deps): Bump docs/themes/hugo-theme-relearn from be85052 to bd1f3d3 (#4348) dependabot[bot] 2024-12-09 20:09:26 +0000
  • c6ccf250fa ⬆️ Update ggerganov/llama.cpp #4353 mudler 2024-12-09 20:07:35 +0000
  • 336acc4a88
    chore(deps): Bump causal-conv1d in /backend/python/mamba #4352 dependabot[bot] 2024-12-09 18:58:42 +0000
  • c1ef1d1021
    chore(deps): Bump mamba-ssm from 2.2.2 to 2.2.4 in /backend/python/mamba #4351 dependabot[bot] 2024-12-09 18:58:32 +0000
  • 20b0bd6566
    chore(deps): Bump gradio in /backend/python/openvoice #4350 dependabot[bot] 2024-12-09 18:31:19 +0000
  • f83afdb146
    chore(deps): Bump numpy in /backend/python/openvoice #4349 dependabot[bot] 2024-12-09 18:31:04 +0000
  • 5134174b36
    chore(deps): Bump docs/themes/hugo-theme-relearn #4348 dependabot[bot] 2024-12-09 18:10:49 +0000
  • f45d6c746a
    chore(model gallery): add tulu-3.1-8b-supernova-smart (#4347) Ettore Di Giacinto 2024-12-09 15:58:29 +0100
  • 7ce782557f chore(model gallery): add tulu-3.1-8b-supernova-smart #4347 Ettore Di Giacinto 2024-12-09 15:56:59 +0100
  • 5eceb5f67c
    chore(model gallery): add impish_mind_8b (#4344) Ettore Di Giacinto 2024-12-09 10:24:30 +0100
  • a9c0dd3a1e
    chore(model gallery): add qwen2.5-7b-homeranvita-nerdmix (#4343) Ettore Di Giacinto 2024-12-09 10:24:15 +0100
  • 4fbd0407f1 chore(model gallery): add qwen2.5-7b-homeranvita-nerdmix #4343 Ettore Di Giacinto 2024-12-09 09:29:33 +0100
  • 4e18be71c1 chore(model gallery): add impish_mind_8b #4344 Ettore Di Giacinto 2024-12-09 09:27:43 +0100
  • fb17e737f0
    docs: ⬆️ update docs version mudler/LocalAI (#4341) LocalAI [bot] 2024-12-09 09:19:25 +0100
  • b5a21202ed
    chore: ⬆️ Update ggerganov/llama.cpp to e52522b8694ae73abf12feb18d29168674aa1c1b (#4342) LocalAI [bot] 2024-12-08 23:54:06 +0100
  • 96e499c7d4 ⬆️ Update ggerganov/llama.cpp #4342 mudler 2024-12-08 20:07:00 +0000
  • 0392fd3c4b ⬆️ Update docs version mudler/LocalAI #4341 mudler 2024-12-08 20:04:34 +0000
  • e147f1bd3e
    chore(model gallery): add bio-medical-llama-3-8b (#4339) Ettore Di Giacinto 2024-12-08 18:43:26 +0100
  • f9c93935b8 chore(model gallery): add bio-medical-llama-3-8b #4339 Ettore Di Giacinto 2024-12-08 18:03:39 +0100
  • 61839efed2
    chore(model gallery): add virtuoso-small (#4338) Ettore Di Giacinto 2024-12-08 18:01:25 +0100
  • a0fe050055
    chore(model gallery): add mn-chunky-lotus-12b (#4337) Ettore Di Giacinto 2024-12-08 18:01:16 +0100
  • 43aa8570e8 chore(model gallery): add virtuoso-small #4338 Ettore Di Giacinto 2024-12-08 17:59:59 +0100
  • e451b82336 chore(model gallery): add mn-chunky-lotus-12b #4337 Ettore Di Giacinto 2024-12-08 17:58:11 +0100
  • f943c4b803
    Revert "feat: include tokens usage for streamed output" (#4336) Ettore Di Giacinto 2024-12-08 17:53:36 +0100
  • 184fbc26bf Revert "feat: include tokens usage for streamed output (#4282)" v2.24.1 release/v2.24.1 Ettore Di Giacinto 2024-12-08 16:31:48 +0100
  • e407fd415b
    Revert "feat: include tokens usage for streamed output (#4282)" #4336 Ettore Di Giacinto 2024-12-08 16:28:43 +0100
  • cea5a0ea42
    feat(template): read jinja templates from gguf files (#4332) Ettore Di Giacinto 2024-12-08 13:50:33 +0100
  • 56f6ab4187
    Merge branch 'master' into read_template #4332 Ettore Di Giacinto 2024-12-08 12:06:18 +0100
  • f47f344836 Small refactoring and adaptations Ettore Di Giacinto 2024-12-08 12:02:41 +0100