Commit graph

  • 55aa4aaf0f add langchain examples Jeffrey Morgan 2023-08-09 11:49:22 -07:00
  • 820f95c4c4 add example Jeffrey Morgan 2023-08-10 20:13:47 -07:00
  • 3a05d3def7
    Merge pull request #326 from asarturas/document-num-gqa-parameter Michael Yang 2023-08-10 18:18:38 -07:00
  • edac9c2446
    Merge pull request #325 from jmorganca/mxyng/typo Michael Yang 2023-08-10 17:30:02 -07:00
  • d9c2687fd0
    document default num_gqa to 1, as it's applicable to most models Arturas Smorgun 2023-08-11 01:29:40 +01:00
  • 6517bcc53c
    Merge pull request #290 from jmorganca/add-adapter-layers Michael Yang 2023-08-10 17:23:01 -07:00
  • 4f54f25b66
    Merge pull request #272 from jmorganca/decode-ggml-2 Michael Yang 2023-08-10 17:22:48 -07:00
  • 6a6828bddf
    Merge pull request #167 from jmorganca/decode-ggml Michael Yang 2023-08-10 17:22:40 -07:00
  • c0e7a3b90e
    Document num_gqa parameter Arturas Smorgun 2023-08-11 00:58:09 +01:00
  • f27bc261cf s/parmeter/parameter/ Michael Yang 2023-08-10 16:26:06 -07:00
  • 21e6197c0b
    Merge pull request #322 from jmorganca/no-comment-warning Michael Yang 2023-08-10 16:24:41 -07:00
  • 75d7d681c9
    Merge pull request #323 from jmorganca/fix-convert-int Michael Yang 2023-08-10 16:24:33 -07:00
  • 81d8d7b73f fix could not convert int Michael Yang 2023-08-10 16:18:55 -07:00
  • 5c0de09a07
    Merge pull request #321 from jmorganca/fix-parameters Michael Yang 2023-08-10 16:23:10 -07:00
  • 20bf000e55 no warning on comments Michael Yang 2023-08-10 16:22:08 -07:00
  • 40d0c4a1dc length check for parameters Michael Yang 2023-08-10 16:09:02 -07:00
  • be889b2f81 add docs for /api/embeddings Jeffrey Morgan 2023-08-10 15:56:59 -07:00
  • 7e26a8df31 cmd: use environment variables for server options Jeffrey Morgan 2023-08-10 14:17:53 -07:00
  • 4ab1da38ba guard around id() Jeffrey Morgan 2023-08-10 14:11:54 -07:00
  • be989d89d1
    Token auth (#314) Patrick Devine 2023-08-10 11:34:25 -07:00
  • bea683e3bf
    cmd: check GetBlobsPath error (#317) Soroush Javadi 2023-08-10 20:27:49 +03:30
  • 178237d37f tweak README.md Jeffrey Morgan 2023-08-10 09:54:03 -07:00
  • 76a678af34 app: dont always show installer window on top now that it lives in the dock Jeffrey Morgan 2023-08-10 09:53:46 -07:00
  • f65169b13e clean up cli flags Jeffrey Morgan 2023-08-10 09:28:56 -07:00
  • 040a5b9750 clean up cli flags Jeffrey Morgan 2023-08-10 09:27:03 -07:00
  • 37c9a8eea9 add lora docs Michael Yang 2023-08-09 15:21:39 -07:00
  • 6de5d032e1 implement loading ggml lora adapters through the modelfile Michael Yang 2023-08-03 17:16:05 -07:00
  • d791df75dd check memory requirements before loading Michael Yang 2023-08-03 15:47:36 -07:00
  • 020a3b3530 disable gpu for q5_0, q5_1, q8_0 quants Michael Yang 2023-08-03 15:40:16 -07:00
  • fccf8d179f partial decode ggml bin for more info Michael Yang 2023-07-21 13:33:56 -07:00
  • 5b5cc9c9f1
    embeddings endpoint Bruce MacDonald 2023-08-10 11:49:55 -04:00
  • 4b3507f036 embeddings endpoint Bruce MacDonald 2023-08-08 15:13:22 -04:00
  • 5ebce03c77
    Add an example on multiline input (#311) Jun Tian 2023-08-10 23:22:28 +08:00
  • 5e25f801ed
    fix a typo in the tweetwriter example Modelfile Bruce MacDonald 2023-08-10 10:19:53 -04:00
  • 8e1234b758
    fix embeddings invalid values Bruce MacDonald 2023-08-10 10:17:00 -04:00
  • 10885986b8 fix a typo in the tweetwriter example Modelfile Soroush Javadi 2023-08-10 15:12:48 +03:30
  • 984c9c628c fix embeddings invalid values Bruce MacDonald 2023-08-09 16:13:24 -04:00
  • 43c40c500e add embed docs for modelfile Bruce MacDonald 2023-08-09 16:14:58 -04:00
  • c4861360ec remove embed docs Bruce MacDonald 2023-08-09 16:14:19 -04:00
  • 9738ef85db
    allow for concurrent pulls of the same files Bruce MacDonald 2023-08-09 11:35:24 -04:00
  • ac971c56d1 Update images.go Bruce MacDonald 2023-08-09 10:40:46 -04:00
  • 8228d166ce pr comments Bruce MacDonald 2023-08-01 15:34:52 -04:00
  • 907e6c56b3 unlock downloadu in case or requestDownload err Bruce MacDonald 2023-07-31 15:44:57 -04:00
  • 868e3b31c7 allow for concurrent pulls of the same files Bruce MacDonald 2023-07-25 17:08:51 -04:00
  • 09d8bf6730 fix build errors Bruce MacDonald 2023-08-09 10:45:57 -04:00
  • 7a5f3616fd
    embed text document in modelfile Bruce MacDonald 2023-08-09 10:26:19 -04:00
  • cff002b824 use content type application/x-ndjson for streaming responses Jeffrey Morgan 2023-08-08 21:38:10 -07:00
  • 55cf5021f0 update langchain example to include python Jeffrey Morgan 2023-08-08 21:03:10 -07:00
  • f58caa5ab5 update README.md Jeffrey Morgan 2023-08-08 15:50:23 -07:00
  • 82df473ec9 use note syntax in README.md Jeffrey Morgan 2023-08-08 15:49:50 -07:00
  • e184c1d035 Link to api.md in README.md Jeffrey Morgan 2023-08-08 15:48:47 -07:00
  • 371d4e5df3 docs: fix invalid json in api.md Jeffrey Morgan 2023-08-08 15:46:05 -07:00
  • 1f78e409b4 docs: format with prettier Jeffrey Morgan 2023-08-08 15:41:48 -07:00
  • 34a88cd776 docs: update api.md formatting Jeffrey Morgan 2023-08-08 15:41:19 -07:00
  • 1bee2347be pr feedback Bruce MacDonald 2023-08-08 16:56:48 -04:00
  • a027a7dd65 add 0.0.0.0 as an allowed origin by default Jeffrey Morgan 2023-08-08 13:39:50 -07:00
  • 22986ccb38 add llama2:70b to the model library list Jeffrey Morgan 2023-08-08 13:08:05 -07:00
  • 884d78ceb3 allow embedding from model binary Bruce MacDonald 2023-08-08 14:38:57 -04:00
  • 3ceac05108 Add embedding docs Bruce MacDonald 2023-08-08 14:04:11 -04:00
  • 21ddcaa1f1 pr comments Bruce MacDonald 2023-08-08 13:49:37 -04:00
  • f2074ed4c0
    Merge pull request #306 from jmorganca/default-keep-system Michael Yang 2023-08-08 09:25:34 -07:00
  • a6f6d18f83 embed text document in modelfile Bruce MacDonald 2023-08-04 18:56:40 -04:00
  • 34a13a9d05
    pass flags to serve to allow setting allowed-origins + host and port Bruce MacDonald 2023-08-08 10:41:42 -04:00
  • 8713ac23a8 allow overriding template and system in /api/generate Jeffrey Morgan 2023-08-08 00:55:34 -04:00
  • 5eb712f962 trim whitespace before checking stop conditions Jeffrey Morgan 2023-08-08 00:27:55 -04:00
  • 4dc5b117dd automatically set num_keep if num_keep < 0 Michael Yang 2023-08-07 14:51:31 -07:00
  • 931a5f3cb9
    Merge pull request #304 from jmorganca/matt/docs Matt Williams 2023-08-07 15:14:06 -07:00
  • 639288bf2b make ollama binary executable on build Jeffrey Morgan 2023-08-07 18:10:37 -04:00
  • d112c15d58 remove old library and web directories Jeffrey Morgan 2023-08-07 18:09:24 -04:00
  • 1267895e44 missed a backtick Matt Williams 2023-08-07 13:53:49 -07:00
  • 089d03bc8d
    Merge pull request #289 from jmorganca/docs Matt Williams 2023-08-07 13:46:22 -07:00
  • e37f4c4f42 DockerIt example Matt Williams 2023-08-07 13:45:22 -07:00
  • ab3ced9d32
    Merge pull request #276 from jmorganca/rope-freq Michael Yang 2023-08-07 13:39:38 -07:00
  • 0c52b4509b get rid of namespace and site Matt Williams 2023-08-07 13:27:58 -07:00
  • 13aace3d34 clarify some more Matt Williams 2023-08-07 13:21:54 -07:00
  • 2b3bb41598 model name format added Matt Williams 2023-08-07 13:17:16 -07:00
  • 93492f1e18 correct precedence of serve params (args over env over default) cmiller01 2023-08-07 19:55:20 +00:00
  • 54ba3e2ceb
    langchain JS integration (#302) Michael Chiang 2023-08-07 12:21:36 -04:00
  • 4904cd8bcd update simpler code samples Matt Williams 2023-08-07 07:40:38 -07:00
  • 8a45359ec6
    Update docs/api.md Matt Williams 2023-08-07 07:33:05 -07:00
  • fb593b7bfc pass flags to serve to allow setting allowed-origins + host and port cmiller01 2023-08-07 03:34:37 +00:00
  • 2544b8afa1 update as per Mike's comments Matt Williams 2023-08-04 17:41:28 -07:00
  • ac1b04f271
    Update docs/api.md Matt Williams 2023-08-04 17:40:52 -07:00
  • 123fdeb919
    Update docs/api.md Matt Williams 2023-08-04 17:38:52 -07:00
  • 5c82bf95d1
    Update docs/api.md Matt Williams 2023-08-04 17:12:24 -07:00
  • 38a9b1618c missed some quotes Matt Williams 2023-08-04 16:09:07 -07:00
  • c18be72a3b complete 1st draft of api docs Matt Williams 2023-08-04 16:08:11 -07:00
  • a101fe51a7 clean up Matt Williams 2023-08-04 12:56:41 -07:00
  • 06fc48ad66
    Update README.md (#285) Bruce MacDonald 2023-08-04 15:45:55 -04:00
  • d93e2f9210 fleshing out response Matt Williams 2023-08-04 12:38:58 -07:00
  • 31edc829fc continuing Matt Williams 2023-08-04 12:30:23 -07:00
  • b31104768c filling out generate Matt Williams 2023-08-04 12:27:47 -07:00
  • b662d9fd8c starting to build out some docs Matt Williams 2023-08-04 11:55:00 -07:00
  • da36196d79 Update the modelfile needed to override the system prompt from orca and make it easier for a downstream user to define their system prompt Matt Williams 2023-08-04 08:11:24 -07:00
  • b9f4d67554 configurable rope frequency parameters Michael Yang 2023-08-03 22:10:49 -07:00
  • 42903973b7 Added an example to generate a list of 10 tweets Matt Williams 2023-08-03 17:26:05 -07:00
  • 8f2df948ab Create a sentiments example Matt Williams 2023-08-03 16:38:31 -07:00
  • e3fb1fd3f1 server: compare options correctly Jeffrey Morgan 2023-08-03 15:55:35 -04:00
  • 29b897f525
    Merge pull request #253 from jmorganca/upload Michael Yang 2023-08-03 12:11:23 -07:00
  • 85aeb42869
    Merge pull request #270 from jmorganca/update-llama-cpp Michael Yang 2023-08-03 12:09:00 -07:00