Commit graph

  • a9a875ee2b
    ⬆️ Bump llama.cpp (#33) Ettore Di Giacinto 2023-04-17 21:34:02 +02:00
  • d3105f25f8 ⬆️ Bump llama.cpp mudler 2023-04-17 21:31:20 +02:00
  • db5ac715f3
    Use a reasonable default context size (#31) Ettore Di Giacinto 2023-04-17 18:45:42 +02:00
  • c33bbdf1a2 Use a reasonable default context size mudler 2023-04-17 18:45:19 +02:00
  • 0b330d90ad
    feat: drop embedded webui (#27) v0.9.2 Ettore Di Giacinto 2023-04-16 10:46:20 +02:00
  • 85184e22e1 feat: drop embedded webui mudler 2023-04-16 10:45:32 +02:00
  • 63601fabd1
    feat: drop default model and llama-specific API (#26) v0.9.1 Ettore Di Giacinto 2023-04-16 10:40:50 +02:00
  • 57bbdde0c3 feat: drop default model and llama-specific API mudler 2023-04-16 10:36:01 +02:00
  • 1370b4482f
    📖 Add prompt-templates examples (#25) Ettore Di Giacinto 2023-04-16 10:24:15 +02:00
  • 6cd241d343 📖 Add prompt-templates examples mudler 2023-04-16 10:23:07 +02:00
  • b062f3142b
    feat: enhance API, expose more parameters (#24) Ettore Di Giacinto 2023-04-16 10:16:48 +02:00
  • 035df63ae8 feat: enhance API, expose more parameters mudler 2023-04-16 10:04:38 +02:00
  • c37175271f
    feature: makefile & updates (#23) Marc R Kellerman 2023-04-15 16:39:07 -07:00
  • f33c293f93
    Merge pull request #18 from go-skynet/feature/devcontainer Ettore Di Giacinto 2023-04-16 01:28:02 +02:00
  • 09dd1a4987 Drop .devcontainer, until its really working mudler 2023-04-16 01:24:54 +02:00
  • 56b630e5eb Keep the latest image specified, to allow no-builds mudler 2023-04-16 01:08:22 +02:00
  • 4394a68889 No sleep for the main container mudler 2023-04-16 01:07:16 +02:00
  • d5a5571d0e Merge branch 'feature/devcontainer' of https://github.com/go-skynet/llama-cli into feature/devcontainer Marc R Kellerman 2023-04-15 16:05:55 -07:00
  • 467dcbd7bd Update docker-compose.yml Marc R Kellerman 2023-04-15 16:05:38 -07:00
  • 1e49f92f80 Minor fixes due to rebase mudler 2023-04-16 01:04:33 +02:00
  • c04c24396d Merge branch 'feature/devcontainer' of https://github.com/go-skynet/llama-cli into feature/devcontainer Marc R Kellerman 2023-04-15 15:59:40 -07:00
  • d72ab3a2ff Update launch.json Marc R Kellerman 2023-04-15 15:59:32 -07:00
  • 7fdff40a34 Go tidy mudler 2023-04-16 00:58:54 +02:00
  • dbd087988f Use .env variables in docker-compose mudler 2023-04-16 00:54:20 +02:00
  • 3f8d5aaeb3 Cleanup makefile mudler 2023-04-16 00:48:05 +02:00
  • 1d877bd70b fixes Marc R Kellerman 2023-04-15 15:38:57 -07:00
  • daea8e158e Revert "latest changes" Marc R Kellerman 2023-04-15 15:26:34 -07:00
  • 50339456b0 Revert "Merge branch 'master' into feature/devcontainer" Marc R Kellerman 2023-04-15 15:24:53 -07:00
  • 56f2b743df
    Merge branch 'master' into feature/devcontainer Marc R Kellerman 2023-04-15 15:23:22 -07:00
  • 5fab6ab544 latest changes Marc R Kellerman 2023-04-15 15:16:29 -07:00
  • 08167ea730 Merge branch 'master' into feature/devcontainer Marc R Kellerman 2023-04-15 15:07:48 -07:00
  • e8eab66c30
    Merge pull request #22 from go-skynet/update-llama.cpp v0.9 Ettore Di Giacinto 2023-04-16 00:06:52 +02:00
  • a73a497143 Update llama.cpp mudler 2023-04-15 23:57:00 +02:00
  • 6aea515e1d
    Merge pull request #20 from go-skynet/mudler-patch-1 Ettore Di Giacinto 2023-04-15 00:38:30 +02:00
  • dfc2b7e02a
    📖 Update README.md Ettore Di Giacinto 2023-04-15 00:38:18 +02:00
  • 040290971c
    Merge pull request #19 from go-skynet/tags Ettore Di Giacinto 2023-04-15 00:14:47 +02:00
  • 553bad585e Use tags for go-llama.cpp mudler 2023-04-15 00:07:39 +02:00
  • ad18b83054 fix case of env variable Marc R Kellerman 2023-04-13 23:08:29 -07:00
  • c2c6ffb23f add Makefile for ease of use Marc R Kellerman 2023-04-13 23:06:58 -07:00
  • 5133476c78 add vscode devcontainer and launch task Marc R Kellerman 2023-04-13 23:06:38 -07:00
  • f76b612506
    Merge pull request #17 from go-skynet/mudler-patch-1 Ettore Di Giacinto 2023-04-13 15:21:13 +02:00
  • c4e94c88d7
    Fix comment typo Ettore Di Giacinto 2023-04-13 15:20:51 +02:00
  • a9cd6b3ca3 ci: Fix tag detection for 'latest' v0.8.1 mudler 2023-04-13 01:37:09 +02:00
  • e786576b95 Update README v0.8 mudler 2023-04-13 01:28:15 +02:00
  • d426571789
    Merge pull request #16 from go-skynet/fix_arm Ettore Di Giacinto 2023-04-13 01:21:58 +02:00
  • a896a2b5ad Drop armv7 builds mudler 2023-04-13 01:21:40 +02:00
  • 8273cd5c04
    Merge pull request #15 from go-skynet/docker-compose Ettore Di Giacinto 2023-04-13 01:17:44 +02:00
  • 16f1281d38 Minor workflow fixes mudler 2023-04-13 01:16:13 +02:00
  • 8042e9a2d6 Add docker-compose mudler 2023-04-13 01:13:14 +02:00
  • 624092cb99 Update README v0.7 mudler 2023-04-12 00:07:30 +02:00
  • a422a883ac Minor rephrasing mudler 2023-04-12 00:04:15 +02:00
  • 7858a97254 Update README mudler 2023-04-12 00:02:47 +02:00
  • 5556aa46dd Small refinements and refactors mudler 2023-04-12 00:02:39 +02:00
  • eb4257f946 Add .gitignore mudler 2023-04-11 23:44:00 +02:00
  • ae30bd346d Reorganize repository layout mudler 2023-04-11 23:43:43 +02:00
  • 93d8977ba2 Return model list v0.6 mudler 2023-04-10 12:02:40 +02:00
  • f43aeeb4a1 Add both API endpoints (completion, chat) mudler 2023-04-09 12:30:55 +02:00
  • c17dcc5e9d Allow to inject prompt as part of the call mudler 2023-04-09 09:36:19 +02:00
  • 4a932483e1 Small fixup to template loading mudler 2023-04-08 11:59:40 +02:00
  • b710147b95 Add mutex on same models (parallel isn't supported yet) mudler 2023-04-08 11:45:36 +02:00
  • ba70363330 Use template input mudler 2023-04-08 11:24:25 +02:00
  • 9fb581739b Allow to template model prompts inputs mudler 2023-04-08 10:46:51 +02:00
  • 48aca246e3 Drop unused interactive mode mudler 2023-04-07 11:31:14 +02:00
  • 12eee097b7 Make it compatible with openAI api, support multiple models mudler 2023-04-07 11:30:59 +02:00
  • b33d015b8c Use go-llama.cpp mudler 2023-04-07 10:08:15 +02:00
  • b7c0a108f5
    Update README.md v0.5 Ettore Di Giacinto 2023-04-05 22:28:03 +02:00
  • f694a89c28
    Update README.md Ettore Di Giacinto 2023-04-05 22:14:00 +02:00
  • be682e6c2f
    Update README.md Ettore Di Giacinto 2023-04-05 22:04:35 +02:00
  • bf85a31f9e Don't set a default model path mudler 2023-04-05 22:00:15 +02:00
  • d69048e0b0
    Update README.md Ettore Di Giacinto 2023-04-05 00:41:02 +02:00
  • 827f189163 Update README mudler 2023-03-30 18:46:11 +02:00
  • a23deb5ec7 Drop duplicate target v0.4 mudler 2023-03-29 19:44:41 +02:00
  • 999676b106 Add gpt4all instructions mudler 2023-03-29 18:58:54 +02:00
  • c61b023bc8 Drop fat images, will document how to consume models mudler 2023-03-29 18:55:24 +02:00
  • 650a22aef1 Add compatibility to gpt4all models mudler 2023-03-29 18:53:24 +02:00
  • 17b1724f7c Update llama-go mudler 2023-03-27 01:18:14 +02:00
  • e860e62036 Add mutex, build only lite images mudler 2023-03-27 01:01:10 +02:00
  • 1f45ff8cd6
    Update README.md Ettore Di Giacinto 2023-03-26 23:37:26 +02:00
  • abee34f60a Cleanup leftover mudler 2023-03-25 01:10:50 +01:00
  • dbc70dc13c Add a simple web-page as index of the API for helping with inference testing mudler 2023-03-25 01:09:51 +01:00
  • 55142065eb Update README with building instructions mudler 2023-03-24 01:11:13 +01:00
  • d83d2293b5 Update version in kubernetes deployment mudler 2023-03-23 23:22:43 +01:00
  • 467ce5a7aa Update models download instructions, update images mudler 2023-03-23 22:06:41 +01:00
  • 4c9c5ce4ce Update README on instruction on how to prompt with the API v0.3 v0.2 mudler 2023-03-23 19:25:28 +01:00
  • 6394d85ca2 Lower conversion parallelism mudler 2023-03-23 19:22:23 +01:00
  • 2b6a5aef5f Lower earthly parallelism mudler 2023-03-23 19:17:15 +01:00
  • d191ecb9fe Disable release pipeline mudler 2023-03-23 19:14:39 +01:00
  • e14e1b0a77 Update README mudler 2023-03-23 18:57:25 +01:00
  • bffaf2aa42 Build images without model mudler 2023-03-23 18:50:43 +01:00
  • d98d1fe55e Use models from model repository mudler 2023-03-23 18:44:24 +01:00
  • 0785cb6b0b Update README with 13B and 30B model instructions mudler 2023-03-22 00:18:48 +01:00
  • f88d5ad829 Update MODEL_URL mudler 2023-03-21 22:03:20 +01:00
  • c7119a2882
    Use tagged image in kubernetes deployment Ettore Di Giacinto 2023-03-21 21:33:11 +01:00
  • 8324402b49 Add interactive.go mudler 2023-03-21 19:21:58 +01:00
  • 9ba30c9c44 Update llama-go, allow to set context-size and enable alpaca model by default mudler 2023-03-21 19:20:23 +01:00
  • 973042bb4c Update README to use tagged container images mudler 2023-03-21 18:45:59 +01:00
  • 3ed2888646 Update README mudler 2023-03-20 23:26:29 +01:00
  • 593ff6308c Add simple client mudler 2023-03-20 23:25:39 +01:00
  • 4275bfc8c0 Add README v0.1 mudler 2023-03-20 21:30:55 +01:00
  • 065815f947 Add kubernetes deployment sample mudler 2023-03-20 21:28:08 +01:00