baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Commit graph

  • 47c2b947a9
         Merge pull request #6546 from ollama/mxyng/fix-test Michael Yang 2024-08-28 15:37:47 -0700
  • 5eb77bf976
         Merge pull request #6539 from ollama/mxyng/validate-modelpath Michael Yang 2024-08-28 14:38:27 -0700
  • e4d0a9c325 fix(test): do not clobber models directory Michael Yang 2024-08-28 14:07:48 -0700
  • 7416ced70f
         add llama3.1 chat template (#6545) Patrick Devine 2024-08-28 14:03:20 -0700
  • 9cfd2dd3e3
         Merge pull request #6522 from ollama/mxyng/detect-chat Michael Yang 2024-08-28 11:04:18 -0700
  • 8e6da3cbc5 update deprecated warnings Michael Yang 2024-08-27 17:57:34 -0700
  • d9d50c43cc validate model path Michael Yang 2024-08-27 17:56:04 -0700
  • 6c1c1ad6a9
         throw an error when encountering unsupport tensor sizes (#6538) Patrick Devine 2024-08-27 17:54:04 -0700
  • 93ea9240ae
         Move ollama executable out of bin dir (#6535) Daniel Hiltgen 2024-08-27 16:19:00 -0700
  • 413ae39f3c update templates to use messages Michael Yang 2024-08-27 11:34:30 -0700
  • 60e47573a6 more tokenizer tests Michael Yang 2024-08-27 11:11:53 -0700
  • d13c3daa0b
         add safetensors to the modelfile docs (#6532) Patrick Devine 2024-08-27 14:46:47 -0700
  • 1713eddcd0
         Fix import image width (#6528) Patrick Devine 2024-08-27 14:19:47 -0700
  • 4e1c4f6e0b
         Update manual instructions with discrete ROCm bundle (#6445) Daniel Hiltgen 2024-08-27 13:42:28 -0700
  • 397cae7962
         llm: fix typo in comment (#6530) Sean Khatiri 2024-08-27 16:28:29 -0400
  • 1c70a00f71 adjust image sizes Patrick Devine 2024-08-27 11:15:25 -0700
  • eae3af6807 clean up convert tokenizer Michael Yang 2024-08-27 10:45:39 -0700
  • 3eb08377f8 detect chat template from configs that contain lists Michael Yang 2024-08-26 16:36:50 -0700
  • ac80010db8
         update the import docs (#6104) Patrick Devine 2024-08-26 19:57:26 -0700
  • 47fa0839b9
         server: clean up route names for consistency (#6524) Jeffrey Morgan 2024-08-26 19:36:11 -0700
  • 0c61920bc9
         Merge https://github.com/ollama/ollama baalajimaestro 2024-08-25 22:02:07 +0530
  • 0f92b19bec
         Only enable numa on CPUs (#6484) Daniel Hiltgen 2024-08-24 17:24:50 -0700
  • 69be940bf6
         gpu: Group GPU Library sets by variant (#6483) Daniel Hiltgen 2024-08-23 15:11:56 -0700
  • 9638c24c58
         Merge pull request #5446 from ollama/mxyng/faq Michael Yang 2024-08-23 14:05:59 -0700
  • bb362caf88 update faq Michael Yang 2024-07-02 15:02:07 -0700
  • 386af6c1a0 passthrough OLLAMA_HOST path to client Michael Yang 2024-08-23 13:16:30 -0700
  • 0c819e167b
         convert safetensor adapters into GGUF (#6327) Patrick Devine 2024-08-23 11:29:56 -0700
  • 7a1e1c1caf
         gpu: Ensure driver version set before variant (#6480) Daniel Hiltgen 2024-08-23 11:21:12 -0700
  • 0b03b9c32f
         llm: Align cmake define for cuda no peer copy (#6455) Daniel Hiltgen 2024-08-23 11:20:39 -0700
  • 90ca84172c
         Fix embeddings memory corruption (#6467) Daniel Hiltgen 2024-08-22 14:51:42 -0700
  • 6bd8a4b0a1
         Merge pull request #6064 from ollama/mxyng/convert-llama3 Michael Yang 2024-08-21 12:57:09 -0700
  • 77903ab8b4 llama3.1 Michael Yang 2024-07-29 14:53:02 -0700
  • e22286c9e1
         Merge pull request #5365 from ollama/mxyng/convert-gemma2 Michael Yang 2024-08-21 11:48:43 -0700
  • 107f695929
         Merge pull request #4917 from ollama/mxyng/convert-bert Michael Yang 2024-08-21 11:48:29 -0700
  • 4ecc70d3b4
         Merge pull request #6386 from zwwhdls/fix-new-layer Michael Yang 2024-08-21 10:58:45 -0700
  • 3546bbd08c convert gemma2 Michael Yang 2024-06-28 13:27:05 -0700
  • beb49eef65 create bert models from cli Michael Yang 2024-06-07 14:55:56 -0700
  • 5a28b9cf5f bert Michael Yang 2024-06-06 08:59:04 -0700
  • a017cf2fea
         Split rocm back out of bundle (#6432) Daniel Hiltgen 2024-08-20 07:26:38 -0700
  • 19e5a890f7
         CI: remove directories from dist dir before upload step (#6429) Daniel Hiltgen 2024-08-19 15:19:21 -0700
  • f91c9e3709
         CI: handle directories during checksum (#6427) Daniel Hiltgen 2024-08-19 13:48:45 -0700
  • 2df6905ede
         Merge pull request #6424 from dhiltgen/cuda_v12 Daniel Hiltgen 2024-08-19 12:11:58 -0700
  • d8be22e47d Fix overlapping artifact name on CI Daniel Hiltgen 2024-08-19 12:07:18 -0700
  • 652c273f0e
         Merge pull request #5049 from dhiltgen/cuda_v12 Daniel Hiltgen 2024-08-19 11:14:24 -0700
  • 88e7705079
         Merge pull request #6402 from rick-github/numParallel Daniel Hiltgen 2024-08-19 11:07:22 -0700
  • f9e31da946 Review comments Daniel Hiltgen 2024-08-15 14:38:14 -0700
  • 88bb9e3328 Adjust layout to bin+lib/ollama Daniel Hiltgen 2024-08-14 16:32:57 -0700
  • 3b19cdba2a Remove Jetpack Daniel Hiltgen 2024-08-13 13:30:28 -0700
  • 927d98a6cd Add windows cuda v12 + v11 support Daniel Hiltgen 2024-07-12 14:33:13 -0700
  • f6c811b320 Enable cuda v12 flags Daniel Hiltgen 2024-07-12 11:35:41 -0700
  • 4fe3a556fa Add cuda v12 variant and selection logic Daniel Hiltgen 2024-06-13 20:46:14 -0700
  • fc3b4cda89 Report GPU variant in log Daniel Hiltgen 2024-06-19 09:36:30 -0700
  • d470ebe78b Add Jetson cuda variants for arm Daniel Hiltgen 2024-05-30 21:54:07 -0700
  • c7bcb00319 Wire up ccache and pigz in the docker based build Daniel Hiltgen 2024-08-09 07:21:40 -0700
  • 74d45f0102 Refactor linux packaging Daniel Hiltgen 2024-07-08 12:50:11 -0700
  • 9fddef3731
         server: limit upload parts to 16 (#6411) Jeffrey Morgan 2024-08-19 09:20:52 -0700
  • 885cf45087 Fix white space. Richard Lyons 2024-08-18 03:07:16 +0200
  • 9352eeb752 Reset NumCtx. Richard Lyons 2024-08-18 02:55:01 +0200
  • 0ad0e738cd Override numParallel only if unset. Richard Lyons 2024-08-18 01:43:26 +0200
  • bdc4308afb fix: chmod new layer to 0o644 when creating it zwwhdls 2024-08-16 11:43:19 +0800
  • d29cd4c2ed
         Merge pull request #6381 from eust-w/main Daniel Hiltgen 2024-08-15 15:31:15 -0700
  • a84c05cf91 fix: Add tooltip to system tray icon eust-w 2024-08-16 06:00:12 +0800
  • e3d7f32af7
         Merge pull request #6363 from ollama/mxyng/fix-noprune Michael Yang 2024-08-15 12:20:38 -0700
  • 3a75e74e34 only skip invalid json manifests Michael Yang 2024-08-15 10:29:14 -0700
  • 99dfb67553
         Alter system prompt baalajimaestro 2024-08-15 22:14:45 +0530
  • 8b4905e4bb
         Merge https://github.com/ollama/ollama baalajimaestro 2024-08-15 21:33:58 +0530
  • ad651e9682
         Use plain golang images instead of oneapi devkit baalajimaestro 2024-08-15 21:33:43 +0530
  • 237dccba1e skip invalid manifest files Michael Yang 2024-08-14 16:36:07 -0700
  • b3f75fc812 fix noprune Michael Yang 2024-08-14 14:37:51 -0700
  • 8200c371ae
         add CONTRIBUTING.md (#6349) Jeffrey Morgan 2024-08-14 15:19:50 -0700
  • 9e08c23ba9
         Merge https://github.com/ollama/ollama baalajimaestro 2024-08-14 21:04:15 +0530
  • 0a8d6ea86d
         Fix typo and improve readability (#5964) longtao 2024-08-14 08:54:19 +0800
  • 8e1050f366
         server: reduce max connections used in download (#6347) Blake Mizerany 2024-08-13 16:47:35 -0700
  • eda8a32a09
         update chatml template format to latest in docs (#6344) Bruce MacDonald 2024-08-13 23:39:18 +0000
  • a0a40aa20c
         Merge pull request #6346 from ollama/mxyng/lint Michael Yang 2024-08-13 14:58:35 -0700
  • 2697d7f5aa lint Michael Yang 2024-08-13 13:40:37 -0700
  • 1f32276178
         Update openai.md to remove extra checkbox (#6345) Pamela Fox 2024-08-13 13:36:05 -0700
  • 4c4fe3f87f
         Merge pull request #6343 from dhiltgen/revert_win_go_version Daniel Hiltgen 2024-08-13 11:53:49 -0700
  • feedf49c71 Go back to a pinned Go version Daniel Hiltgen 2024-08-13 11:44:50 -0700
  • 8b00a415ab
         Load Embedding Model on Empty Input (#6325) royjhan 2024-08-13 13:19:56 -0400
  • 01b80e9ffc
         Merge pull request #5443 from ollama/mxyng/convert-phi3 Michael Yang 2024-08-12 15:47:58 -0700
  • bd5e432630 update import.md Michael Yang 2024-08-05 10:30:32 -0700
  • aec77d6a05 support new "longrope" attention factor Bruce MacDonald 2024-07-02 14:40:01 -0700
  • 6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128 Michael Yang 2024-06-03 15:53:58 -0700
  • f7e3b9190f
         cmd: spinner progress for transfer model data (#6100) Josh 2024-08-12 11:46:32 -0700
  • 980dd15f81
         cmd: speed up gguf creates (#6324) Josh 2024-08-12 11:46:09 -0700
  • 01d544d373
         OpenAI: Simplify input output in testing (#5858) royjhan 2024-08-12 13:33:34 -0400
  • 1dc3ef3aa9
         Revert "server: speed up single gguf creates (#5898)" (#6323) Josh 2024-08-12 09:57:51 -0700
  • 8aac22438e
         server: speed up single gguf creates (#5898) Josh 2024-08-12 09:28:55 -0700
  • 15c2d8fe14
         server: parallelize embeddings in API web handler instead of in subprocess runner (#6220) Jeffrey Morgan 2024-08-11 11:57:10 -0700
  • 25906d72d1
         llm: prevent loading too large models on windows (#5926) Daniel Hiltgen 2024-08-11 11:30:20 -0700
  • 023451ce47
         add integration obook-summary (#6305) CognitiveTech 2024-08-10 21:43:08 -0400
  • 9b53e39d8e
         Merge pull request #6258 from coolljt0725/fix_typo Jesse Gross 2024-08-09 17:19:48 -0700
  • 97fae2df95
         Merge pull request #6235 from Nicholas42/fix_line_endings Michael Yang 2024-08-09 17:06:30 -0700
  • 160d9d4900
         Merge pull request #6171 from ollama/mxyng/remove-temp Michael Yang 2024-08-09 15:47:13 -0700
  • d4e6407464 Restrict text files with explicit line feeds to *.go. Nicholas Schwab 2024-08-09 23:14:13 +0200
  • b7f7d8cd15
         Merge pull request #6291 from dhiltgen/no_sparse_fail Daniel Hiltgen 2024-08-09 12:30:25 -0700
  • 2fa1db4345 Don't hard fail on sparse setup error Daniel Hiltgen 2024-08-09 11:57:48 -0700
  • 71b0945fc6
         Merge pull request #6290 from dhiltgen/intel_npe Daniel Hiltgen 2024-08-09 12:14:42 -0700
  • 5bca2e60a7 Harden intel boostrap for nil pointers Daniel Hiltgen 2024-08-09 11:31:38 -0700