Commit Graph

  • fd037cc8b2 comments Patrick Devine 2024-08-12 18:00:09 -07:00
  • b5082ab9ac fix unittests Patrick Devine 2024-08-12 14:30:54 -07:00
  • fa354b1338 convert safetensor adapters into GGUF Patrick Devine 2024-08-12 14:16:05 -07:00
  • 9ee3d79f9b no load on invalid input Roy Han 2024-08-12 16:55:41 -07:00
  • 01b80e9ffc
    Merge pull request #5443 from ollama/mxyng/convert-phi3 Michael Yang 2024-08-12 15:47:58 -07:00
  • bd5e432630 update import.md Michael Yang 2024-08-05 10:30:32 -07:00
  • aec77d6a05 support new "longrope" attention factor Bruce MacDonald 2024-07-02 14:40:01 -07:00
  • 6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128 Michael Yang 2024-06-03 15:53:58 -07:00
  • 0fa601d59c add systemd environment configuration Sergey Korablin 2024-08-12 23:15:03 +03:00
  • f84cc9939c allow ollama.com to call inference and info endpoints brucemacd/allow-ollama Bruce MacDonald 2024-08-09 09:31:09 -07:00
  • f7e3b9190f
    cmd: spinner progress for transfer model data (#6100) Josh 2024-08-12 11:46:32 -07:00
  • 980dd15f81
    cmd: speed up gguf creates (#6324) Josh 2024-08-12 11:46:09 -07:00
  • 781585d9bd return 204 for cross-origin OPTIONS royh/ep-methods Roy Han 2024-07-10 12:52:34 -07:00
  • b84a54be05 return 405 for bad method Roy Han 2024-07-10 11:23:48 -07:00
  • 5762957eb8 load on empty input Roy Han 2024-08-12 11:22:43 -07:00
  • d50d393ff8 lint Josh Yan 2024-08-12 10:59:16 -07:00
  • 36d2bb2934 atomic values Josh Yan 2024-08-01 11:56:35 -07:00
  • d7698b3813 transfer progress on main Josh Yan 2024-07-30 17:31:15 -07:00
  • 01d544d373
    OpenAI: Simplify input output in testing (#5858) royjhan 2024-08-12 13:33:34 -04:00
  • 830e4b7924 rebase Josh Yan 2024-08-12 10:25:19 -07:00
  • 1dc3ef3aa9
    Revert "server: speed up single gguf creates (#5898)" (#6323) Josh 2024-08-12 09:57:51 -07:00
  • 1e675036ba
    Revert "server: speed up single gguf creates (#5898)" Josh 2024-08-12 09:52:56 -07:00
  • 8aac22438e
    server: speed up single gguf creates (#5898) Josh 2024-08-12 09:28:55 -07:00
  • c50fd5c136 refactor test Josh Yan 2024-08-06 09:51:44 -07:00
  • 3a4d393f70 rework test Josh Yan 2024-08-05 11:42:51 -07:00
  • 924002b145 rewrite test Josh Yan 2024-08-05 10:51:48 -07:00
  • 92047c04cd log Josh Yan 2024-08-05 10:38:36 -07:00
  • 15e6a4fbd4 move err Josh Yan 2024-08-05 10:28:11 -07:00
  • 0dbd1aeb06 remove println Josh Yan 2024-08-01 11:18:31 -07:00
  • d5802e3079 lint Josh Yan 2024-08-01 11:17:38 -07:00
  • 27550da129 report err Josh Yan 2024-07-31 11:47:36 -07:00
  • 6df1f76369 test complete Josh Yan 2024-07-24 14:09:15 -07:00
  • 7d424ea906 test Josh Yan 2024-07-24 13:51:28 -07:00
  • 9cc312a04b reuse gguf Josh Yan 2024-07-24 11:07:14 -07:00
  • 620413d262 test setup Josh Yan 2024-07-24 11:05:52 -07:00
  • fed007fde0 vroom Josh Yan 2024-07-23 17:20:51 -07:00
  • 4675771441
    Merge branch 'main' into patch-1 Sam 2024-08-12 12:41:19 +10:00
  • 412e427783
    Merge 3803ecb6a699492ec7b82de8e2714bff8fd65e5f into 15c2d8fe149ba2b58aadbab615a6955f8821c7a9 Michael Yang 2024-08-11 22:13:25 -04:00
  • 85c175f18c
    Merge 2ff004b4a9d329de7154ce7a20cdba922d3970e6 into 15c2d8fe149ba2b58aadbab615a6955f8821c7a9 joecryptotoo 2024-08-11 21:07:13 -04:00
  • 23b9c5556c
    Merge 0e6db0772150b923ea4ea9ba252a70afde1c5eca into 15c2d8fe149ba2b58aadbab615a6955f8821c7a9 Eric Curtin 2024-08-11 20:36:42 -04:00
  • d768cbd886
    Merge f9d20611dc896679a6071e3e44d573c3db309351 into 15c2d8fe149ba2b58aadbab615a6955f8821c7a9 Eric Curtin 2024-08-11 20:01:03 -04:00
  • a42b619d49
    Merge 0c01c5a5b7209bf03f5f3cf6bc2ad6a87a00d701 into 15c2d8fe149ba2b58aadbab615a6955f8821c7a9 Jerry Liu 2024-08-11 19:15:25 -04:00
  • 15c2d8fe14
    server: parallelize embeddings in API web handler instead of in subprocess runner (#6220) v0.3.5 Jeffrey Morgan 2024-08-11 11:57:10 -07:00
  • 25906d72d1
    llm: prevent loading too large models on windows (#5926) Daniel Hiltgen 2024-08-11 11:30:20 -07:00
  • b6194cce8a lint jmorganca 2024-08-11 10:35:42 -07:00
  • dd5fc2983b added a go example for mistral's native function calling Binozo 2024-08-11 12:07:22 +02:00
  • 023451ce47
    add integration obook-summary (#6305) CognitiveTech 2024-08-10 21:43:08 -04:00
  • efa6cd6650
    add integration obook-summary CognitiveTech 2024-08-10 21:36:42 -04:00
  • be3f21c71c
    Install Ollama with winget Nikita Lukianets 2024-08-10 12:32:05 +03:00
  • 9b53e39d8e
    Merge pull request #6258 from coolljt0725/fix_typo Jesse Gross 2024-08-09 17:19:48 -07:00
  • 97fae2df95
    Merge pull request #6235 from Nicholas42/fix_line_endings Michael Yang 2024-08-09 17:06:30 -07:00
  • 160d9d4900
    Merge pull request #6171 from ollama/mxyng/remove-temp Michael Yang 2024-08-09 15:47:13 -07:00
  • d4e6407464 Restrict text files with explicit line feeds to *.go. Nicholas Schwab 2024-08-09 23:14:13 +02:00
  • b7f7d8cd15
    Merge pull request #6291 from dhiltgen/no_sparse_fail Daniel Hiltgen 2024-08-09 12:30:25 -07:00
  • 2fa1db4345 Don't hard fail on sparse setup error Daniel Hiltgen 2024-08-09 11:57:48 -07:00
  • 71b0945fc6
    Merge pull request #6290 from dhiltgen/intel_npe Daniel Hiltgen 2024-08-09 12:14:42 -07:00
  • 30823ec925 update readme royh/whisper Roy Han 2024-08-09 11:32:27 -07:00
  • 5bca2e60a7 Harden intel boostrap for nil pointers Daniel Hiltgen 2024-08-09 11:31:38 -07:00
  • 89f3bae306 cli Roy Han 2024-08-09 11:04:26 -07:00
  • 67472e0e89
    Also flag *.icns as binary Nicholas42 2024-08-09 13:41:20 +02:00
  • 8299af4974
    docs(tools): add ingest Sam 2024-08-09 21:33:43 +12:00
  • 9b31d8f265
    Merge branch 'main' into feature/kv-quant Sam 2024-08-09 18:49:41 +12:00
  • 07c45d6197 cmd: print proxy info when OLLAMA_DEBUG is true zhangyunhao 2024-08-09 06:42:29 +00:00
  • acd571bbf7 fix: improved cache type estimations Sam McLeod 2024-08-09 16:42:23 +10:00
  • 7fe1a97c5d fix: improved cache type estimations Sam McLeod 2024-08-09 08:02:20 +10:00
  • af434c8d62 Adjust arm cuda repo paths Daniel Hiltgen 2024-08-01 17:22:25 -07:00
  • 6e9d7f4795 Catch one more error log Daniel Hiltgen 2024-08-05 09:28:07 -07:00
  • df33076b92 manifest: Store layers inside manifests consistently as values. Jesse Gross 2024-08-07 14:22:17 -07:00
  • 5e9b54a183 image: Clarify argument to WriteManifest is config Jesse Gross 2024-08-07 11:44:25 -07:00
  • 756d91159c add metrics to docs (#6079) royjhan 2024-08-07 17:43:44 -04:00
  • bba9c31315 Wire up native source file dependencies Daniel Hiltgen 2024-08-05 08:56:47 -07:00
  • e9aa5117c4
    Merge pull request #6133 from dhiltgen/cuda_repo Daniel Hiltgen 2024-08-08 12:33:35 -07:00
  • 2473bdba5e
    Merge pull request #6182 from dhiltgen/more_patterns Daniel Hiltgen 2024-08-08 12:33:17 -07:00
  • 2003d60159 llama3.1 memory Michael Yang 2024-08-08 11:18:13 -07:00
  • 7d1c0047fa
    Merge pull request #6247 from ollama/jessegross/layers Jesse Gross 2024-08-08 10:46:43 -07:00
  • 7b61eba471 server/download.go: Fix a typo in log Jitang Lei 2024-08-08 20:28:01 +08:00
  • ffcf987366
    Update api/client.go longtao 2024-08-08 09:58:12 +08:00
  • 7edaf6e7e8 manifest: Store layers inside manifests consistently as values. Jesse Gross 2024-08-07 14:22:17 -07:00
  • 97ec8cfd4e image: Clarify argument to WriteManifest is config Jesse Gross 2024-08-07 11:44:25 -07:00
  • 7e848d983a remove unnecessary temp vars and lock jmorganca 2024-08-07 18:03:04 -04:00
  • 5b3a21b578
    add metrics to docs (#6079) royjhan 2024-08-07 17:43:44 -04:00
  • 5afed62d89
    Merge branch 'ollama:main' into feature/kv-quant Sam 2024-08-08 09:30:27 +12:00
  • ad0c19dde4
    Use llama3.1 in tools example (#5985) Kyle Kelley 2024-08-07 14:20:50 -07:00
  • 2fe945412a get api models mxyng/api-models Michael Yang 2024-08-07 11:43:44 -07:00
  • ad7e822883 audio processing error prop Roy Han 2024-08-07 14:05:22 -07:00
  • d503f04b32 expiration Roy Han 2024-08-07 13:01:04 -07:00
  • 8ccf543c53 chat doc Roy Han 2024-08-06 17:31:51 -07:00
  • 75ad6309b4 chat support Roy Han 2024-08-06 16:42:02 -07:00
  • a5181a8c51 error handling Roy Han 2024-08-06 11:45:13 -07:00
  • 2a9feb0707 model flexibility Roy Han 2024-08-06 10:53:29 -07:00
  • e4d35198a2 transcribe Roy Han 2024-08-05 14:16:32 -07:00
  • 17f9dc6d08 save whisper port Roy Han 2024-08-05 13:19:01 -07:00
  • 97d9dffa80 err check Roy Han 2024-08-02 16:57:34 -07:00
  • 65483180b9 working poc Roy Han 2024-08-02 16:54:28 -07:00
  • 1ac92eae7c submodule Roy Han 2024-07-31 16:23:17 -07:00
  • 69eb06c40e
    Merge pull request #6145 from ollama/jessegross/bug5840 Jesse Gross 2024-08-07 11:24:15 -07:00
  • 1829fb61bd manifest: Fix crash on startup when trying to clean up unused files (#5840) Jesse Gross 2024-08-05 17:13:52 -07:00
  • ce67706037 Set *.png and *.ico to be treated as binary files. Nicholas Schwab 2024-08-07 18:15:17 +02:00
  • 2b4fcfb72a remove unused argument jmorganca 2024-08-07 12:05:17 -04:00
  • 69207b4987 fix memory mxyng/fix-memory Michael Yang 2024-08-06 19:06:40 -07:00