Commit Graph

  • 2674d06fb9
    add embed model command and fix question invoke Shubham 2024-06-01 18:19:09 +05:30
  • 829ff87bd1
    revert tokenize ffi (#4761) v0.1.40 Michael Yang 2024-05-31 18:54:21 -07:00
  • 5f0403d208 Isolated Deletions royh-testdelete Roy Han 2024-05-31 17:40:11 -07:00
  • 95bff5d92f Revert "use ffi for tokenizing/detokenizing" Michael Yang 2024-05-31 17:22:29 -07:00
  • 8241054990 Revert "vocab only" Michael Yang 2024-05-31 17:22:22 -07:00
  • b95e8e8c12 Revert "use int32_t for call to tokenize (#4738)" Michael Yang 2024-05-31 17:22:13 -07:00
  • 5a3cb1064a Clean Up Delete Tests Roy Han 2024-05-31 16:44:54 -07:00
  • f6b622c4b3
    Merge pull request #4733 from ollama/jyan/isvalidname Josh 2024-05-31 14:08:45 -07:00
  • 77487ada72 Err Check Roy Han 2024-05-31 13:12:26 -07:00
  • a946b6f020 Adjust Response and Blob Check Roy Han 2024-05-31 13:08:59 -07:00
  • c62df6b3bf Check Blob Roy Han 2024-05-31 12:07:52 -07:00
  • 2e4da8eec2 added tests for IsValidNamespace Josh Yan 2024-05-31 11:48:07 -07:00
  • e8788ae8dd Specify DNE error Roy Han 2024-05-31 09:45:47 -07:00
  • 889548bfc0 Add golang pprof longhui.li 2024-05-31 22:42:49 +08:00
  • e2fbb9bfe6
    Merge branch 'ollama:main' into main Klimenty Titov 2024-05-31 11:38:05 +03:00
  • 95af97b9f3 server: try github.com/minio/sha256-simd bmizerany/fastverify Blake Mizerany 2024-05-31 00:42:09 -07:00
  • 763bb65dbb
    use int32_t for call to tokenize (#4738) v0.1.40-rc1 Jeffrey Morgan 2024-05-30 21:43:30 -07:00
  • 7ca9605f54
    speed up tests by only building static lib (#4740) Jeffrey Morgan 2024-05-30 21:43:15 -07:00
  • a0086e3677 fix crash jmorganca 2024-05-30 21:39:35 -07:00
  • d5c11e628c cleanup jmorganca 2024-05-30 21:38:01 -07:00
  • e4905e227e speed up tests by only building static lib jmorganca 2024-05-30 21:28:31 -07:00
  • 452a325ad0 variable naming jmorganca 2024-05-30 21:06:26 -07:00
  • 2b1f638d5c use int32_t for call to tokenize jmorganca 2024-05-30 21:01:19 -07:00
  • 6186c56c99 Add OLLAMA_MAX_DOWNLOAD_PARTS env to support config parallel download parts Lei Jitang 2024-05-25 10:52:54 +08:00
  • eb2c443a79
    Merge pull request #4736 from ollama/mxyng/vocab-only Michael Yang 2024-05-30 17:21:00 -07:00
  • 278e25ea44
    Merge pull request #4737 from ollama/mxyng/less-generate Michael Yang 2024-05-30 17:17:50 -07:00
  • a50a87a7b8
    partial offloading: allow flash attention and disable mmap (#4734) Jeffrey Morgan 2024-05-30 16:58:01 -07:00
  • 98085015d5 only generate on relevant changes Michael Yang 2024-05-22 09:58:26 -07:00
  • bf54c845e9 vocab only Michael Yang 2024-05-30 16:49:28 -07:00
  • 7078a01a2e allow mmap with num_gpu=0 jmorganca 2024-05-30 16:44:26 -07:00
  • 8774e5d6a9 Deletion Unit Test Roy Han 2024-05-30 16:44:17 -07:00
  • c365f195a8 directly use isvalidpart Josh Yan 2024-05-30 16:40:04 -07:00
  • 562b0aa53f partial offloading: allow flash attention and disable mmap jmorganca 2024-05-30 16:38:38 -07:00
  • e91d0ef737
    Merge pull request #4728 from ollama/jyan/japanese Josh 2024-05-30 16:25:12 -07:00
  • 22f5c12ced
    Update llama.cpp submodule to 5921b8f0 (#4731) Jeffrey Morgan 2024-05-30 16:20:22 -07:00
  • 298c996e54 added IsValidNamespace function Josh Yan 2024-05-30 16:02:07 -07:00
  • 5386a59683 add patch jmorganca 2024-05-30 14:36:28 -07:00
  • 66d936196e update llama.cpp submodule to 5921b8f089d3b7bda86aac5a66825df6a6c10603 jmorganca 2024-05-30 14:22:11 -07:00
  • 0fc0cfc6d2
    Merge pull request #4594 from dhiltgen/doc_container_workarounds Daniel Hiltgen 2024-05-30 13:10:54 -07:00
  • 914f68f021 replaced duplicate call with variable Josh Yan 2024-05-30 10:38:07 -07:00
  • bd1d119ba9 fixed japanese characters deleted at end of line Josh Yan 2024-05-30 10:24:21 -07:00
  • a03be18189
    Fix OLLAMA_LLM_LIBRARY with wrong map name and add more env vars to help message (#4663) Lei Jitang 2024-05-31 00:36:51 +08:00
  • d4a23e0700 making go-chat iterative Yalun 2024-05-30 23:51:22 +08:00
  • 59f8aad003 docs: update to add LLocal.in to web & desktop integrations kartikm7 2024-05-30 16:41:25 +05:30
  • 13f80092d1
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-30 07:02:23 +03:00
  • 2337a1fbf7 server: skip blob verification for already verified blobs Blake Mizerany 2024-05-24 08:40:40 -07:00
  • c79fd5c168 Reincluding Numbers language_support Roy Han 2024-05-29 12:22:36 -07:00
  • 96bc232b43
    Merge pull request #4413 from ollama/mxyng/name-check Michael Yang 2024-05-29 12:06:58 -07:00
  • bca7b12284
    Merge pull request #3718 from ollama/mxyng/modelname-3 Michael Yang 2024-05-29 12:02:07 -07:00
  • 32cb1960c1
    Merge pull request #4380 from ollama/mxyng/tokenize Michael Yang 2024-05-29 12:00:59 -07:00
  • 73fb9ea36e Draft for Multi-Language Modelfile Creation Roy Han 2024-05-29 11:51:57 -07:00
  • de781b37c8 rm unused infill Michael Yang 2024-05-12 09:21:35 -07:00
  • 3e21799377 rm unused system prompt Michael Yang 2024-05-12 09:20:39 -07:00
  • 26a00a0410 use ffi for tokenizing/detokenizing Michael Yang 2024-05-11 12:49:24 -07:00
  • abe628d8ab
    Create monitoring.md patcher9 2024-05-29 12:35:52 +05:30
  • 8005b6040d serve: Add more env to help message of ollama serve Lei Jitang 2024-05-27 20:45:04 +08:00
  • 646371f56d
    Merge pull request #3278 from zhewang1-intc/rebase_ollama_main Daniel Hiltgen 2024-05-28 16:30:50 -07:00
  • 161aa75f1b - cobra shell completions nanvenomous 2024-05-28 17:37:02 -05:00
  • 1f5008544b
    Update install.sh Jeffrey Morgan 2024-05-28 15:01:22 -07:00
  • 45cbfc5aee
    fix wsl2 status check for nvidia cards (#4689) Jeffrey Morgan 2024-05-28 14:49:46 -07:00
  • 57d9fa2b23 fix wsl2 status check for nvidia cards jmorganca 2024-05-28 14:49:21 -07:00
  • 6d423b383b
    Improve install experience on WSL2 and Linux (#4653) Jeffrey Morgan 2024-05-28 14:41:50 -07:00
  • ad897080a2
    working on integration of multi-byte and multi-width runes (#4549) v0.1.39 Josh 2024-05-28 12:04:03 -07:00
  • 9b02af3211 fixed remove() Josh Yan 2024-05-28 11:49:07 -07:00
  • 2beeb90a13 added helper to retrieve lineSpacing, renamed lineFlags for clarity Josh Yan 2024-05-28 11:39:29 -07:00
  • b7d316d98d
    fix nvidia detection in install script (#4683) Jeffrey Morgan 2024-05-28 09:59:36 -07:00
  • 959c4be1ee fix nvidia detection in install script jmorganca 2024-05-28 09:57:28 -07:00
  • d7339fad52
    Merge pull request #4682 from dhiltgen/more_time Daniel Hiltgen 2024-05-28 09:36:02 -07:00
  • 92c81e8117 Give the final model loading more time Daniel Hiltgen 2024-05-28 08:56:18 -07:00
  • 300f30b589
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-28 13:31:25 +03:00
  • 9db0996ed4
    Add OllamaSpring Project to Readme (#4672) Tai 2024-05-28 10:58:26 +08:00
  • 394d8fb0e8
    Update README.md Jeffrey Morgan 2024-05-27 19:58:15 -07:00
  • eff0d9f595 Add OllamaSpring Project to Readme neil 2024-05-28 10:53:37 +08:00
  • 6f43898b17
    Adds olpaka flutter client (#4647) Orfeo Ciano 2024-05-28 01:22:01 +01:00
  • 5c24f83933
    Update README.md Jeffrey Morgan 2024-05-27 17:21:38 -07:00
  • 7487229c34
    llm/server.go: Fix 2 minor typos (#4661) Lei Jitang 2024-05-28 08:21:10 +08:00
  • 8a8e7afa96
    small fix on examples/python-simplechat/client.py to actually get a streamed response and get tokens printed as we receive it (#4671) Rayan Mostovoi 2024-05-28 02:19:20 +02:00
  • ba4291cedf small fix on examples/python-simplechat/client.py to actually get a streamed response and get tokens printed as we receive it Rayan Mostovoi 2024-05-27 23:30:11 +02:00
  • d83c20715a
    Merge branch 'ollama:main' into main Климентий Титов 2024-05-27 21:06:48 +03:00
  • 35fe4579e9
    Merge remote-tracking branch 'upstream/main' Gamunu Balagalla 2024-05-27 21:28:39 +05:30
  • c1ff99ee70 envconfig/config.go: Fix wrong description of OLLAMA_LLM_LIBRARY Lei Jitang 2024-05-27 20:22:26 +08:00
  • a8e8b837a8 llm/server.go: Fix 2 minor typos Lei Jitang 2024-05-27 19:44:39 +08:00
  • cdbc51f233 feat: add OLLAMA_HOME for default keypath Maas Lalani 2024-05-27 01:23:46 -04:00
  • 9a096e2481 Improve install experience on WSL2 and Linux jmorganca 2024-05-26 16:14:23 -07:00
  • c79f8c9c39
    Ensure nvidia and nvidia_uvm kernel modules are loaded in install.sh script and at startup (#4652) Jeffrey Morgan 2024-05-26 14:57:17 -07:00
  • 43dbbfa131 consistent success message for AMD jmorganca 2024-05-26 14:48:23 -07:00
  • a6e0e0b9dc restart if nouveau is detected jmorganca 2024-05-26 14:28:35 -07:00
  • 9c65d1feea use SUDO variable jmorganca 2024-05-26 11:55:21 -07:00
  • 90dff36be8 indentation jmorganca 2024-05-26 11:54:55 -07:00
  • 033a458fe5 ensure kernel modules are loaded in install.sh script and at startup jmorganca 2024-05-26 11:53:14 -07:00
  • 485016bfbb
    Update install.sh Jeffrey Morgan 2024-05-26 11:46:00 -07:00
  • bdecf1cda7
    Update README.md with node-red-contrib-ollama in the Extensions & Plugins section Jakub Burkiewicz 2024-05-26 15:18:00 +02:00
  • 12ae5d8123 Adds olpaka flutter client Orfeo 2024-05-26 12:50:21 +01:00
  • 50784b6375
    Merge 6e7cde9469a8a1055acc1c55a91095b05f8925cd into 0165ba1651aea1be5a498d8fabbb7c3c0c2b3608 Alfred Nutile 2024-05-26 02:52:09 +03:00
  • 16b50c4cd6
    Merge 1b5fe3a34b4f141968845fcf459f28943131080d into 0165ba1651aea1be5a498d8fabbb7c3c0c2b3608 Eric Curtin 2024-05-25 23:39:10 +02:00
  • 0165ba1651
    Merge pull request #4638 from dhiltgen/better_error Daniel Hiltgen 2024-05-25 14:32:28 -07:00
  • b6ffecf6f9 consolidate changes eli 2024-05-25 21:46:19 +03:00
  • 8611e48688 add vision compatibility eli 2024-05-25 21:05:35 +03:00
  • c4209d6d21 Report better warning on client closed abort of load Daniel Hiltgen 2024-05-25 09:23:28 -07:00
  • 1c41dd20b8 Add support for the new OpenAI API structure eli 2024-05-25 18:45:56 +03:00