Commit Graph

  • 3e95725452 update patches jmorganca 2024-07-22 11:27:12 -04:00
  • 1860fb94e7 update to d94c6e0c jmorganca 2024-07-22 11:24:32 -04:00
  • 305ebda32f Lowercase hostname for CORS. Richard Lyons 2024-07-22 15:19:03 +02:00
  • 3f1b53fe97 Update llama.cpp submodule to 1bdd8ae1 zhongTao99 2024-07-19 22:44:19 +14:00
  • 23cb550d0a add lora support jmorganca 2024-07-21 16:14:22 -04:00
  • 7a6e1f2d4f fix patches jmorganca 2024-07-20 14:20:57 -04:00
  • c80e9f81a1 upate commit jmorganca 2024-07-20 14:18:52 -04:00
  • 20b7a56438 Add 'finish_reason': 'tool_calls' when tools are called Yevhen Vitruk 2024-07-21 21:25:02 +03:00
  • 3134eba759 Add 'finish_reason': 'tool_calls' when tools are called Yevhen Vitruk 2024-07-21 15:27:52 +03:00
  • f0a06cae0b Added Chrome and Firefox extension link to documentation ivostoykov 2024-07-21 10:22:37 +01:00
  • fa0e2e5837
    Merge 56905d4b10c803d94d6d7dadd3912faf17bbb3c6 into 80ee9b5e47fc0ea99d1f3f33224923266627c15c Andrei Bondarev 2024-07-21 12:54:03 +08:00
  • 72ba263a4f remove workaround jmorganca 2024-07-20 23:59:15 -04:00
  • 45417e4b0e server: collect nested tool call objects when parsing jmorganca 2024-07-20 23:57:19 -04:00
  • 80ee9b5e47
    Remove out of space test temporarily (#5825) Jeffrey Morgan 2024-07-21 00:22:11 -04:00
  • c8b238c73f remove for now jmorganca 2024-07-21 00:16:03 -04:00
  • b38e9cadae sched: fix out of space test jmorganca 2024-07-21 00:07:25 -04:00
  • 5534f2cc6a
    llm: consider head_dim in llama arch (#5817) v0.2.8-rc1 Jeffrey Morgan 2024-07-20 21:48:12 -04:00
  • d321297d8a
    Merge pull request #5815 from dhiltgen/win_rocm_gfx_features Daniel Hiltgen 2024-07-20 16:02:55 -07:00
  • 06e5d74e34
    Merge pull request #5506 from dhiltgen/sched_tests Daniel Hiltgen 2024-07-20 15:48:39 -07:00
  • 5d707e6fd5
    Merge pull request #5583 from dhiltgen/integration_improvements Daniel Hiltgen 2024-07-20 15:48:21 -07:00
  • 283948c83b Adjust windows ROCm discovery Daniel Hiltgen 2024-07-19 15:07:26 -07:00
  • c0f2cc7074 Expose GPU discovery failure information Daniel Hiltgen 2024-07-20 14:58:25 -07:00
  • 2407b25826 convert: capture head_dim for mistral jmorganca 2024-07-20 18:16:00 -04:00
  • 43f51375cd llm: consider head_dim in llama arch jmorganca 2024-07-20 18:11:05 -04:00
  • 1475eab95f
    add patch for tekken (#5807) Jeffrey Morgan 2024-07-20 13:41:21 -04:00
  • 9bc92ae915 add patch for tekken jmorganca 2024-07-20 01:23:00 -04:00
  • 20090f3172
    preserve last assistant message (#5802) Jeffrey Morgan 2024-07-19 20:19:26 -07:00
  • 7d67d6f3d9 template: fix mistral not adding system prompt if assistant is last message jmorganca/template-mistral jmorganca 2024-07-19 18:21:22 -07:00
  • 69a2d4ccff
    Fix generate test flakyness (#5804) Jeffrey Morgan 2024-07-19 19:11:25 -07:00
  • de28e5b5ad actually fix loading instead... jmorganca 2024-07-19 19:06:27 -07:00
  • 8cd66870a0 add comment jmorganca 2024-07-19 19:04:02 -07:00
  • 37d824d85d only skip check on windows jmorganca 2024-07-19 19:00:07 -07:00
  • 711e60635d remove flaky check for now jmorganca 2024-07-19 18:50:42 -07:00
  • a6ded99e0a remove flaky check for now jmorganca 2024-07-19 18:50:02 -07:00
  • cd2fb53d15 remove flaky check for now jmorganca 2024-07-19 18:48:39 -07:00
  • 6384248bfa revert unnecessary change jmorganca 2024-07-19 17:57:17 -07:00
  • 9e40d5f016 revert unnecessary change jmorganca 2024-07-19 17:56:32 -07:00
  • fb7c51d45d simplify jmorganca 2024-07-19 17:55:17 -07:00
  • 9c8eb752fa simplify jmorganca 2024-07-19 17:53:03 -07:00
  • a3a4c793f6 preserve last assistant message jmorganca 2024-07-19 17:47:52 -07:00
  • e8b954c646
    server: validate template (#5734) Josh 2024-07-19 15:24:29 -07:00
  • ca1fbc5789 cmt Josh Yan 2024-07-19 15:23:30 -07:00
  • 9f5b19e217
    Update README.md to add LLMStack integration Ajay Chintala 2024-07-19 11:45:42 -07:00
  • c57317cbf0
    OpenAI: Function Based Testing (#5752) royjhan 2024-07-19 11:37:12 -07:00
  • 22336143fe rm comment Roy Han 2024-07-18 10:22:47 -07:00
  • 68769ed7e2 more coverage Roy Han 2024-07-18 10:20:33 -07:00
  • d000d596bc distinguish error forwarding Roy Han 2024-07-17 11:16:14 -07:00
  • 51b2fd299c
    adjust openai chat msg processing (#5729) royjhan 2024-07-19 11:19:20 -07:00
  • cdb6e87a40
    Merge branch 'main' into patch-1 Daniel Nguyen 2024-07-19 11:12:17 +07:00
  • 56905d4b10 Add hermes-2-pro-llama-3 to the testing matrix Andrei Bondarev 2024-07-18 16:20:52 -04:00
  • d0634b1596
    Merge pull request #5780 from ollama/mxyng/tools v0.2.7 Michael Yang 2024-07-18 12:14:10 -07:00
  • 43606d6d6a fix parsing tool calls Michael Yang 2024-07-18 12:07:59 -07:00
  • 70b1010fa5
    server: check for empty tools array too (#5779) Jeffrey Morgan 2024-07-18 11:44:57 -07:00
  • b41c9a1871 server: check for empty tools array too jmorganca 2024-07-18 11:42:55 -07:00
  • 84e5721f3a
    always provide content even if empty (#5778) Jeffrey Morgan 2024-07-18 11:28:19 -07:00
  • 2601f5c9f6 always provide content even if empty jmorganca 2024-07-18 11:23:38 -07:00
  • 319fb1ce03
    server: only parse tool calls if tools are provided (#5771) v0.2.6 Jeffrey Morgan 2024-07-18 08:50:23 -07:00
  • a60afc514d still set resp.Message.Content jmorganca 2024-07-18 08:30:47 -07:00
  • 70d92c6f12 server: only parse tool calls if tools are provided jmorganca 2024-07-18 08:25:57 -07:00
  • 459c8a8e55 Add Verbis project to README Alex Mavrogiannis 2024-07-18 18:24:15 +03:00
  • db2aa6cd88 Add Ollama-GUI to web & desktop chyok 2024-07-18 18:53:44 +08:00
  • cda0a71a2f adding "cache_prompt" to options Daniel Kleine 2024-07-18 11:40:55 +02:00
  • 80d065658d Make llama.cpp's cache_prompt parameter configurable Yap Sok Ann 2024-07-18 08:57:33 +07:00
  • b255445557
    marshal json automatically for some template values (#5758) Michael Yang 2024-07-17 15:35:11 -07:00
  • 0ef1330091 marshal json automatically for some template values Michael Yang 2024-07-17 14:45:29 -07:00
  • f02f83660c bump go version to 1.22.5 to fix security vulnerabilities lreed 2024-07-17 21:44:19 +00:00
  • aaec2be2ee gin header Josh Yan 2024-07-17 12:12:43 -07:00
  • b23424bb3c
    Merge pull request #5753 from ollama/mxyng/parse-tool-call Michael Yang 2024-07-17 11:47:53 -07:00
  • 9b5bf861dd use new err Josh Yan 2024-07-17 11:35:34 -07:00
  • 5fd6988126 parse tool call as individual objects Michael Yang 2024-07-17 11:02:36 -07:00
  • 91431f6446 adjust openai chat msg processing Roy Han 2024-07-16 13:24:21 -07:00
  • 309307c8f9 update test, remove comments jyan/reord-g Josh Yan 2024-07-17 10:46:50 -07:00
  • 5b82960df8
    stub response (#5750) Michael Yang 2024-07-17 10:39:22 -07:00
  • 04e3be691f stub response Michael Yang 2024-07-17 10:26:28 -07:00
  • cc9a252d8c
    Merge pull request #5732 from ollama/mxyng/cleanup Michael Yang 2024-07-17 10:26:54 -07:00
  • d281a6e603
    add sidellama link (#5702) Pákozdi György 2024-07-17 19:24:44 +02:00
  • 53aca40ffd
    Merge branch 'main' into patch-1 Michael 2024-07-17 10:24:12 -07:00
  • 3e89435605 bad request to templ err Josh Yan 2024-07-17 09:59:20 -07:00
  • 8d5dbcbbf8
    Merge ebf8b7251ce20d2238a300f7d030d9841eb0d20e into 154f6f45d4acd4ea1f2e35cac3b90eb6faeea6bd Nahian Pathan 2024-07-17 14:04:41 +01:00
  • 34cf218498
    Rename README.md to Brazilian-Portuguese-README.md Ítalo Gustavo 2024-07-17 09:29:13 -03:00
  • f4374cb00f readme updated avinash ghadshi 2024-07-17 15:22:26 +05:30
  • 58db8d5b4e readme updated avinash ghadshi 2024-07-17 15:20:32 +05:30
  • ebc2df5428 Added code to use swap memory in linux avinash ghadshi 2024-07-17 15:18:03 +05:30
  • 154f6f45d4
    OpenAI: Support Tools (#5614) royjhan 2024-07-16 20:52:59 -07:00
  • 0d41623b52
    OpenAI: Add Suffix to v1/completions (#5611) royjhan 2024-07-16 20:50:14 -07:00
  • 61bb45659c clean up Roy Han 2024-07-16 20:47:16 -07:00
  • dd319d5d61 mutually exclusive content and tool calls Roy Han 2024-07-16 20:17:50 -07:00
  • 9873fd5719
    openai expects arguments to be a string (#5739) Jeffrey Morgan 2024-07-16 20:14:17 -07:00
  • c8b2fd32b6
    Update amd-igpu-780m.md alexhegit 2024-07-17 10:47:52 +08:00
  • bc7803cd82 openai expects arguments to be a string jmorganca 2024-07-16 19:36:11 -07:00
  • e9aaf842e1 ID and Function Roy Han 2024-07-16 17:43:49 -07:00
  • f7b6cd7934 tests Josh Yan 2024-07-16 17:31:12 -07:00
  • 30707e3c29 remove tc from stream for now Roy Han 2024-07-16 15:25:52 -07:00
  • a1e0415318 tools Roy Han 2024-07-16 12:17:14 -07:00
  • 761b5b683e reopen pr Roy Han 2024-07-16 09:59:35 -07:00
  • 5bfb07b500 validate template Josh Yan 2024-07-16 17:11:39 -07:00
  • 378a1032b1 add suffix Roy Han 2024-07-16 16:55:57 -07:00
  • 568416ba17 add suffix royh-openai-suffixdocs Roy Han 2024-07-10 15:40:22 -07:00
  • 80cba42ab2 Update docs Roy Han 2024-06-26 14:30:28 -07:00
  • 6477a7aca4 Merge branch 'royh-completions-docs' of https://github.com/ollama/ollama into royh-completions-docs royjhan 2024-07-16 16:51:11 -07:00