Commit Graph

  • abb072ff79
    Merge 2a03905920 into b86a3e4fa6 #3352 Ettore Di Giacinto 2024-12-05 17:23:45 +0800
  • b86a3e4fa6
    chore(model gallery): add math-iio-7b-instruct (#4323) Ettore Di Giacinto 2024-12-05 10:05:35 +0100
  • 967ad4a08f chore(model gallery): add math-iio-7b-instruct #4323 Ettore Di Giacinto 2024-12-05 10:03:58 +0100
  • be907d993f
    chore(model gallery): add loki-v2.6-8b-1024k (#4321) Ettore Di Giacinto 2024-12-05 10:02:02 +0100
  • ab0f8648a3
    chore(model gallery): add rp-naughty-v1.0c-8b (#4322) Ettore Di Giacinto 2024-12-05 10:01:49 +0100
  • 29469b70e3 chore(model gallery): add rp-naughty-v1.0c-8b #4322 Ettore Di Giacinto 2024-12-05 09:54:02 +0100
  • 0a435752e9 chore(model gallery): add loki-v2.6-8b-1024k #4321 Ettore Di Giacinto 2024-12-05 09:31:30 +0100
  • c226149503
    chore: ⬆️ Update leejet/stable-diffusion.cpp to 9578fdcc4632dc3de5565f28e2fb16b7c18f8d48 (#4320) LocalAI [bot] 2024-12-05 09:09:11 +0100
  • 4a079f893c
    chore: ⬆️ Update ggerganov/llama.cpp to 59f4db10883a4f3e855cffbf2c3ab68430e95272 (#4319) LocalAI [bot] 2024-12-04 23:19:35 +0100
  • cf650e4cbd ⬆️ Update leejet/stable-diffusion.cpp #4320 mudler 2024-12-04 20:07:45 +0000
  • 4a5069cc48 ⬆️ Update ggerganov/llama.cpp #4319 mudler 2024-12-04 20:07:28 +0000
  • 87b7648591
    chore(ci): set auto-labeler for dependencies v2.24.0 Ettore Di Giacinto 2024-12-04 18:35:54 +0100
  • cf4f024420
    Update README.md Ettore Di Giacinto 2024-12-04 11:31:08 +0100
  • 3c0ac49d90
    chore(model gallery): add bark-cpp-small (#4318) Ettore Di Giacinto 2024-12-04 09:32:42 +0100
  • d70c539342 chore(model gallery): add bark-cpp-small #4318 Ettore Di Giacinto 2024-12-04 09:29:45 +0100
  • 4307ae5d52
    chore(model gallery): add flux.1-dev-ggml (#4317) Ettore Di Giacinto 2024-12-04 09:26:51 +0100
  • b3ff1f1f75 chore(model gallery): add flux.1-dev-ggml #4317 Ettore Di Giacinto 2024-12-04 09:25:14 +0100
  • 50f71f73d7
    chore(model gallery): add homercreativeanvita-mix-qw7b (#4316) Ettore Di Giacinto 2024-12-04 09:17:23 +0100
  • cf59fef1e2 chore(model gallery): add homercreativeanvita-mix-qw7b #4316 Ettore Di Giacinto 2024-12-04 09:16:20 +0100
  • dc04a43868
    chore(model gallery): add chatty-harry_v3.0 (#4315) Ettore Di Giacinto 2024-12-04 09:15:47 +0100
  • cc04b62d3a
    chore(model gallery): add cybercore-qwen-2.1-7b (#4314) Ettore Di Giacinto 2024-12-04 09:15:35 +0100
  • 1b7bf02d2d chore(model gallery): add cybercore-qwen-2.1-7b #4314 Ettore Di Giacinto 2024-12-04 09:12:54 +0100
  • 197371f8ce chore(model gallery): add chatty-harry_v3.0 #4315 Ettore Di Giacinto 2024-12-04 09:10:09 +0100
  • feb54e65c2
    chore: ⬆️ Update ggerganov/llama.cpp to cc98896db858df7aa40d0e16a505883ef196a482 (#4312) LocalAI [bot] 2024-12-04 00:53:11 +0100
  • 1156493d55
    Merge branch 'master' into update/CPPLLAMA_VERSION #4312 Ettore Di Giacinto 2024-12-03 22:41:50 +0100
  • 44a5dac312
    feat(backend): add stablediffusion-ggml (#4289) Ettore Di Giacinto 2024-12-03 22:41:22 +0100
  • c8964f01ee fix: set free_params_immediately to false to call the model in sequence #4289 Ettore Di Giacinto 2024-12-03 22:04:14 +0100
  • b0f724f2f8 ⬆️ Update ggerganov/llama.cpp mudler 2024-12-03 20:07:33 +0000
  • 1f360a7f5b
    Merge branch 'master' into feat/stablediffusion-ggml Ettore Di Giacinto 2024-12-03 19:27:07 +0100
  • bef0d4ffc9 Make it working Ettore Di Giacinto 2024-12-03 19:25:09 +0100
  • 074b52bbfe
    chore(model gallery): add bggpt-gemma-2-2.6b-it-v1.0 (#4311) Ettore Di Giacinto 2024-12-03 18:56:53 +0100
  • 236a60bab8
    chore(model gallery): add qwen2.5-7b-homercreative-mix (#4310) Ettore Di Giacinto 2024-12-03 18:56:03 +0100
  • 7b70f0543b
    chore(model gallery): add sparse-llama-3.1-8b-2of4 (#4309) Ettore Di Giacinto 2024-12-03 18:55:49 +0100
  • cd8c4498e0 chore(model gallery): add qwen2.5-7b-homercreative-mix #4310 Ettore Di Giacinto 2024-12-03 18:51:00 +0100
  • bfe23383ea chore(model gallery): add bggpt-gemma-2-2.6b-it-v1.0 #4311 Ettore Di Giacinto 2024-12-03 18:48:58 +0100
  • 6a43142970 chore(model gallery): add sparse-llama-3.1-8b-2of4 #4309 Ettore Di Giacinto 2024-12-03 18:42:02 +0100
  • 5f33962932
    chore: ⬆️ Update ggerganov/llama.cpp to 8648c521010620c2daccfa1d26015c668ba2c717 (#4307) LocalAI [bot] 2024-12-03 09:20:59 +0100
  • 45b91d501e
    chore(deps): Bump docs/themes/hugo-theme-relearn from 28fce6b to be85052 (#4305) dependabot[bot] 2024-12-02 22:47:37 +0000
  • 9fbeb06c93 ⬆️ Update ggerganov/llama.cpp #4307 mudler 2024-12-02 20:06:19 +0000
  • b693eef541
    chore(deps): Bump grpcio-tools in /backend/python/parler-tts #4306 dependabot[bot] 2024-12-02 19:13:22 +0000
  • e82ea2a981
    chore(deps): Bump docs/themes/hugo-theme-relearn #4305 dependabot[bot] 2024-12-02 18:54:18 +0000
  • a8743ee328
    chore(deps): Bump gradio in /backend/python/openvoice #4304 dependabot[bot] 2024-12-02 18:52:02 +0000
  • 6607310599
    chore(deps): Bump faster-whisper in /backend/python/openvoice #4303 dependabot[bot] 2024-12-02 18:51:37 +0000
  • 3d465c1582
    chore(deps): Bump whisper-timestamped in /backend/python/openvoice #4302 dependabot[bot] 2024-12-02 18:51:33 +0000
  • 606f21520b Move cfg scale out of diffusers block Ettore Di Giacinto 2024-12-02 17:12:02 +0100
  • 354928b914 fixups Ettore Di Giacinto 2024-12-02 17:11:46 +0100
  • 7cca1b2124 Use default scheduler and sampler if not specified Ettore Di Giacinto 2024-11-29 18:47:14 +0100
  • ba20cd7ff4 fixups Ettore Di Giacinto 2024-11-29 18:13:05 +0100
  • c0c4e0da21 chore(ci): track stablediffusion-ggml Ettore Di Giacinto 2024-11-29 18:11:59 +0100
  • 71d82e44e5 feat(backend): add stablediffusion-ggml Ettore Di Giacinto 2024-11-29 18:02:08 +0100
  • e51792784a
    chore(deps): bump grpcio to 1.68.1 (#4301) Ettore Di Giacinto 2024-12-02 19:13:26 +0100
  • fe504f0c29 chore(deps): bump grpcio to 1.68.1 #4301 Ettore Di Giacinto 2024-12-02 19:12:37 +0100
  • 28594336e9
    chore: ⬆️ Update ggerganov/llama.cpp to 5e1ed95583ca552a98d8528b73e1ff81249c2bf9 (#4299) LocalAI [bot] 2024-12-01 22:44:59 +0100
  • 6e628417c2 ⬆️ Update ggerganov/llama.cpp #4299 mudler 2024-12-01 20:06:36 +0000
  • b38ba418d0
    Merge 3a1727a4fe into 9c9359fc96 #2911 Ettore Di Giacinto 2024-12-01 12:54:41 +0000
  • 9c9359fc96
    chore(model gallery): add teleut-7b (#4298) Ettore Di Giacinto 2024-12-01 10:12:48 +0100
  • bc5d1f255b
    chore(model gallery): add skywork-o1-open-llama-3.1-8b (#4297) Ettore Di Giacinto 2024-12-01 10:12:35 +0100
  • 0fcefbc168
    chore(model gallery): add volare-i1 (#4296) Ettore Di Giacinto 2024-12-01 10:12:17 +0100
  • 4f4931a030 chore(model gallery): add teleut-7b #4298 Ettore Di Giacinto 2024-12-01 10:10:36 +0100
  • 4195cf8214 chore(model gallery): add skywork-o1-open-llama-3.1-8b #4297 Ettore Di Giacinto 2024-12-01 10:09:01 +0100
  • ccde46be11 chore(model gallery): add volare-i1 #4296 Ettore Di Giacinto 2024-12-01 10:07:02 +0100
  • 9044b17e4d
    chore: ⬆️ Update ggerganov/llama.cpp to 0c39f44d70d058940fe2afe50cfc789e3e44d756 (#4295) LocalAI [bot] 2024-11-30 22:46:07 +0100
  • 1d2d44d522 ⬆️ Update ggerganov/llama.cpp #4295 mudler 2024-11-30 20:06:24 +0000
  • 1c44f30d47
    Merge 63bd7a5674 into ad31daf03b #1246 Bowen 2024-11-30 17:42:27 +0000
  • ad31daf03b
    chore(model gallery): add qwestion-24b (#4294) Ettore Di Giacinto 2024-11-30 11:18:25 +0100
  • 13890303e8 chore(model gallery): add qwestion-24b #4294 Ettore Di Giacinto 2024-11-30 11:16:52 +0100
  • 1167487f5e
    chore(model gallery): add freyja-v4.95-maldv-7b-non-fiction-i1 (#4293) Ettore Di Giacinto 2024-11-30 11:15:05 +0100
  • aca9be4e0a chore(model gallery): add freyja-v4.95-maldv-7b-non-fiction-i1 #4293 Ettore Di Giacinto 2024-11-30 11:04:24 +0100
  • 61358e4d35
    chore(model gallery): add q2.5-32b-slush-i1 (#4292) Ettore Di Giacinto 2024-11-30 11:02:41 +0100
  • 82124d5b10 chore(model gallery): add q2.5-32b-slush-i1 #4292 Ettore Di Giacinto 2024-11-30 11:00:18 +0100
  • 2c8a87b1e4
    chore: ⬆️ Update ggerganov/llama.cpp to 3a8e9af402f7893423bdab444aa16c5d9a2d429a (#4290) LocalAI [bot] 2024-11-29 22:58:24 +0100
  • a19a7655c5 ⬆️ Update ggerganov/llama.cpp #4290 mudler 2024-11-29 20:06:58 +0000
  • 55aad5f525
    chore: ⬆️ Update ggerganov/llama.cpp to dc22344088a7ee81a1e4f096459b03a72f24ccdc (#4288) LocalAI [bot] 2024-11-29 00:04:31 +0100
  • 5179e4ea05
    Merge branch 'master' into update/CPPLLAMA_VERSION #4288 Ettore Di Giacinto 2024-11-28 22:17:01 +0100
  • 58ff47de26
    feat(bark-cpp): add new bark.cpp backend (#4287) Ettore Di Giacinto 2024-11-28 22:16:44 +0100
  • c3aec9ed3f ⬆️ Update ggerganov/llama.cpp mudler 2024-11-28 20:07:04 +0000
  • 288bfc521b No need to test rwkv specifically, now part of llama.cpp #4287 Ettore Di Giacinto 2024-11-28 17:30:25 +0100
  • 8abaeda244 Drop old entries from bumper Ettore Di Giacinto 2024-11-28 17:30:11 +0100
  • 0a636d3a31 track bark.cpp in CI bumps Ettore Di Giacinto 2024-11-28 16:09:04 +0100
  • b24c8f1280 build on linux only for now Ettore Di Giacinto 2024-11-28 16:05:54 +0100
  • 0d6c3a7d57
    feat: include tokens usage for streamed output (#4282) mintyleaf 2024-11-28 17:47:56 +0400
  • 00af0bb1f6 feat(bark-cpp): add new bark.cpp backend Ettore Di Giacinto 2024-11-28 12:56:33 +0100
  • e001fada6c
    chore(model gallery): add llama-smoltalk-3.2-1b-instruct (#4285) Ettore Di Giacinto 2024-11-28 09:35:38 +0100
  • f4547fcf8a
    chore(model gallery): add qwq-32b-preview (#4284) Ettore Di Giacinto 2024-11-28 09:34:44 +0100
  • 7b75e9de2d
    fix(rwkv model): add stoptoken (#4283) Ettore Di Giacinto 2024-11-28 09:34:35 +0100
  • 97ba781f45 chore(model gallery): add llama-smoltalk-3.2-1b-instruct #4285 Ettore Di Giacinto 2024-11-28 09:33:34 +0100
  • 8971151759 chore(model gallery): add qwq-32b-preview #4284 Ettore Di Giacinto 2024-11-28 09:30:34 +0100
  • 1ce5a826b0 fix(rwkv model): add stoptoken #4283 Ettore Di Giacinto 2024-11-28 09:28:40 +0100
  • e459118de6
    Merge branch 'master' into fix/stream_tokens_usage #4282 Ettore Di Giacinto 2024-11-28 09:23:34 +0100
  • cbedf2f428
    fix(llama.cpp): embed metal file into result binary for darwin (#4279) Ettore Di Giacinto 2024-11-28 05:17:00 +0100
  • 725eecdfa6
    Merge branch 'master' into fix/metal_embed #4279 Dave 2024-11-27 19:50:01 -0500
  • 8e8e05d203
    Merge branch 'master' into fix/stream_tokens_usage mintyleaf 2024-11-28 03:17:34 +0400
  • 2931ea422d Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame mintyleaf 2024-11-28 02:15:19 +0400
  • 0597f3b9e9
    chore: ⬆️ Update ggerganov/llama.cpp to 3ad5451f3b75809e3033e4e577b9f60bcaf6676a (#4280) LocalAI [bot] 2024-11-27 23:24:47 +0100
  • 1d391cdf52 fix(llama.cpp): embed metal file into result binary for darwin Ettore Di Giacinto 2024-11-27 20:04:23 +0100
  • 7d7ace83ac ⬆️ Update ggerganov/llama.cpp #4280 mudler 2024-11-27 20:07:19 +0000
  • 5f688d7a8d
    chore(model): add eva-qwen2.5-72b-v0.2 to the gallery (#4278) Ettore Di Giacinto 2024-11-27 19:02:05 +0100
  • fa20628b3a
    chore(model): add llama-3.1-tulu-3-8b-sft to the gallery (#4277) Ettore Di Giacinto 2024-11-27 19:01:54 +0100
  • ec0927cb02 chore(model): add eva-qwen2.5-72b-v0.2 to the gallery #4278 Ettore Di Giacinto 2024-11-27 18:55:54 +0100
  • 5e5f353385 chore(model): add llama-3.1-tulu-3-8b-sft to the gallery #4277 Ettore Di Giacinto 2024-11-27 18:52:52 +0100