Commit Graph

  • 9245c8a1df add how to quantize doc Matt Williams 2023-10-12 15:34:57 -07:00
  • 7a537cdca9 Merge pull request #770 from jmorganca/mxyng/fix-download Michael Yang 2023-10-12 12:56:43 -07:00
  • 257ffeb997 fix download Michael Yang 2023-10-12 12:52:35 -07:00
  • 9b513bb6b1 Merge pull request #753 from jmorganca/mattw/examplereorg Matt Williams 2023-10-12 11:24:12 -07:00
  • 042100f797 final rename Matt Williams 2023-10-12 11:23:41 -07:00
  • 7804b8fab9 validate api options fields from map (#711) Bruce MacDonald 2023-10-12 11:18:11 -04:00
  • 56497663c8 relay model runner error message to client (#720) Bruce MacDonald 2023-10-12 11:16:37 -04:00
  • e1afcb8af2 simple gen to simple Matt Williams 2023-10-11 21:29:07 -07:00
  • 385eeea357 remove with Matt Williams 2023-10-11 21:26:11 -07:00
  • 8a41b244e8 add golang gen Matt Williams 2023-10-11 21:20:50 -07:00
  • 92578798bb fix relative links in README.md Jeffrey Morgan 2023-10-11 19:24:06 -04:00
  • 788637918a Merge pull request #760 from jmorganca/mxyng/more-downloads Michael Yang 2023-10-11 14:33:10 -07:00
  • c413a55093 download: handle inner errors Michael Yang 2023-10-11 13:49:01 -07:00
  • 630bb75d2a dynamically size download parts based on file size Michael Yang 2023-10-10 17:22:44 -07:00
  • a2055a1e93 update download Michael Yang 2023-10-09 10:14:49 -07:00
  • b599946b74 add format bytes Michael Yang 2023-10-11 10:55:07 -07:00
  • aca2d65b82 Merge pull request #757 from jmorganca/mxyng/format-time Michael Yang 2023-10-11 11:12:29 -07:00
  • b5e08e3373 cleanup format time Michael Yang 2023-10-11 11:05:39 -07:00
  • 274d5a5fdf optional parameter to not stream response (#639) Bruce MacDonald 2023-10-11 12:54:27 -04:00
  • fc6b49be32 add ts alternate to python langchain simplegen Matt Williams 2023-10-11 09:50:15 -07:00
  • 77295f716e prevent waiting on exited command (#752) Bruce MacDonald 2023-10-11 12:32:13 -04:00
  • 615f7d1dea cleanup readme. Matt Williams 2023-10-11 06:13:29 -07:00
  • cdf5e106ae rename dirs Matt Williams 2023-10-11 06:10:24 -07:00
  • a85329f59a rename the models to be more descriptive Matt Williams 2023-10-10 17:40:02 -07:00
  • f2ba1311aa improve vram safety with 5% vram memory buffer (#724) Bruce MacDonald 2023-10-10 16:16:09 -04:00
  • 65dcd0ce35 always cleanup blob download (#747) Jeffrey Morgan 2023-10-10 13:12:29 -04:00
  • 0040f543a2 Merge pull request #743 from jmorganca/mxyng/http-proxy Michael Yang 2023-10-10 09:59:06 -07:00
  • 767f9bdbbb Merge pull request #585 from jmorganca/matt/examplementors Matt Williams 2023-10-09 13:58:14 -07:00
  • f7f5169c94 Update api.md (#741) Costa Alexoglou 2023-10-09 22:01:46 +02:00
  • 2cfffea02e handle client proxy Michael Yang 2023-10-09 12:18:26 -07:00
  • f6e98334e4 handle upstream proxies Michael Yang 2023-10-09 11:42:36 -07:00
  • ab0668293c llm: fix build on amd64 Jeffrey Morgan 2023-10-06 14:39:54 -07:00
  • af4cf55884 not found error before pulling model (#718) Bruce MacDonald 2023-10-06 16:06:20 -04:00
  • d6786f2945 add feedback for reading model metadata (#722) Bruce MacDonald 2023-10-06 16:05:32 -04:00
  • 38dc2f79bc Merge pull request #626 from jmorganca/mxyng/concurrent-downloads Michael Yang 2023-10-06 13:01:29 -07:00
  • cb961c87ca Merge pull request #679 from jamesbraza/modelfile-docs Michael Yang 2023-10-06 12:59:45 -07:00
  • 0560b28a8d names Michael Yang 2023-10-03 17:06:13 -07:00
  • 10199c5987 replace done channel with file check Michael Yang 2023-10-03 16:52:49 -07:00
  • 288814d3e4 fix ref counts Michael Yang 2023-10-03 16:44:35 -07:00
  • 04733438da check head request response Michael Yang 2023-10-03 16:12:53 -07:00
  • 711e891f0f fix resumable downloads Michael Yang 2023-10-02 15:26:27 -07:00
  • 090d08422b handle unexpected eofs Michael Yang 2023-10-02 13:34:07 -07:00
  • 5b84404c64 handle concurrent requests for the same blobs Michael Yang 2023-09-29 16:13:53 -07:00
  • 8544edca21 parallel chunked downloads Michael Yang 2023-09-27 16:22:30 -07:00
  • 5d22319a2c rename server subprocess (#700) Bruce MacDonald 2023-10-06 10:15:42 -04:00
  • 2130c0708b output type parsed from modelfile (#678) Bruce MacDonald 2023-10-05 14:58:04 -04:00
  • 61ff1946e6 revise help text (#706) Patrick Devine 2023-10-05 11:36:07 -07:00
  • d06bc0cb6e enable q8, q5, 5_1, and f32 for linux gpu (#699) Bruce MacDonald 2023-10-05 12:53:47 -04:00
  • d104b7e997 Fix go test./... issue: fmt.Println arg list ends with redundant newline (#705) Alexander F. Rødseth 2023-10-05 17:11:04 +02:00
  • 9e2de1bd2c increase streaming buffer size (#692) Bruce MacDonald 2023-10-04 14:09:00 -04:00
  • dc87e9c9ae update Dockerfile to pass GOFLAGS Jeffrey Morgan 2023-10-03 07:05:09 -07:00
  • 367cb68dc1 Merge pull request #686 from jmorganca/mxyng/starcoder Michael Yang 2023-10-02 22:47:19 -07:00
  • c02c0cd483 starcoder Michael Yang 2023-10-02 19:52:25 -07:00
  • 1852755154 show a default message when license/parameters/system prompt/template aren't specified (#681) v0.1.1 Patrick Devine 2023-10-02 14:34:52 -07:00
  • 6f2ce74231 Got rif of all caps to show it can be lower case James Braza 2023-10-02 13:54:27 -07:00
  • 6edcc5c79f Using code highlighting syntax around Modelfile James Braza 2023-10-02 13:46:05 -07:00
  • b1f7123301 clean up num_gpu calculation code (#673) Bruce MacDonald 2023-10-02 14:53:42 -04:00
  • 1fbf3585d6 Relay default values to llama runner (#672) Bruce MacDonald 2023-10-02 14:53:16 -04:00
  • 99d5161e8a don't wordwrap when stdout is redirected or piped (#662) Patrick Devine 2023-10-02 11:50:55 -07:00
  • ea8380be45 add community project: Chatbot Ollama Michael 2023-10-02 09:04:31 -07:00
  • 4f25092dc1 fix build_docker.sh permissions Jeffrey Morgan 2023-10-01 16:42:32 -07:00
  • 4fc10acce9 add some missing code directives in docs (#664) Jiayu Liu 2023-10-02 02:51:01 +08:00
  • 0a4f21c0a7 fix docker build (#659) Michael Yang 2023-09-30 13:34:01 -07:00
  • 9abb66254a docker: fix volume permission errors Jeffrey Morgan 2023-09-30 12:32:06 -07:00
  • 1d0ebe67e8 Document response stream chunk delimiter. (#632) Jay Nakrani 2023-09-30 00:45:52 -04:00
  • a1b2d95f96 remove unused push/pull params (#650) Bruce MacDonald 2023-09-29 17:27:19 -04:00
  • c0b1bf7537 Merge pull request #606 from jmorganca/mxyng/install.sh-2 Michael Yang 2023-09-29 11:30:46 -07:00
  • cdfeb165ca Merge pull request #608 from jmorganca/mxyng/build Michael Yang 2023-09-29 11:30:25 -07:00
  • 92d454ec5f update build_darwin.sh Michael Yang 2023-09-26 10:38:32 -07:00
  • 9333b0cc82 Merge pull request #612 from jmorganca/mxyng/prune-empty-directories Michael Yang 2023-09-29 11:23:39 -07:00
  • 9771b1ec51 windows runner fixes (#637) Bruce MacDonald 2023-09-29 11:47:55 -04:00
  • 76db4a49cf allow the user to cancel generating with ctrl-C (#641) Patrick Devine 2023-09-28 17:13:01 -07:00
  • 4aa0976a2e Added missing return preventing SIGSEGV because of missing resp (#621) Luc Stepniewski 2023-09-28 23:25:22 +02:00
  • 92c20fdae6 fix error messages for unknown commands in the repl (#611) Patrick Devine 2023-09-28 14:19:45 -07:00
  • c951da7096 Merge pull request #634 from jmorganca/mxyng/int64 Michael Yang 2023-09-28 14:17:47 -07:00
  • 24d82a23a2 do not download updates multiple times (#633) Bruce MacDonald 2023-09-28 15:29:17 -04:00
  • f40b3de758 use int64 consistently Michael Yang 2023-09-28 10:00:34 -07:00
  • 5f4008c296 Update README.md Michael 2023-09-28 09:06:03 -07:00
  • 6ae33d8141 Update modelfile.md to reflect the usage of num_gpu. (#629) Aaron Coffey 2023-09-28 07:21:21 -07:00
  • c5664c1fef Update faq.md Jeffrey Morgan 2023-09-27 13:49:43 -07:00
  • 958a5a8184 revert fedora cuda version check Bruce MacDonald 2023-09-27 15:12:29 -04:00
  • 8608eb4760 prune empty directories Michael Yang 2023-09-26 17:28:14 -07:00
  • a2b210130f fedora install fixes (#609) Bruce MacDonald 2023-09-27 11:43:47 -04:00
  • ed20837f9a Update modelfile.md Bruce MacDonald 2023-09-27 10:38:10 -04:00
  • 1db2a61dd0 Added num_predict to the options table (#614) James Braza 2023-09-27 07:26:08 -07:00
  • 2ded8ab206 use 11.8.0 nvidia dockerfile base image for now Jeffrey Morgan 2023-09-25 23:52:05 -07:00
  • e6b3648bbf Merge pull request #616 from jmorganca/mxyng/fix-model-name Michael Yang 2023-09-26 20:54:18 -07:00
  • 0625e805f0 fix model name not matching Michael Yang 2023-09-26 19:49:55 -07:00
  • c38ec5befb Merge pull request #598 from jmorganca/mxyng/help-exit Michael Yang 2023-09-26 15:17:40 -07:00
  • c577721a43 Merge pull request #605 from jmorganca/mxyng/install.sh Michael Yang 2023-09-26 09:53:05 -07:00
  • 29c056ea39 ordered list of install locations Michael Yang 2023-09-26 09:38:11 -07:00
  • 9fc3bba9cf do no unload nouveau driver Michael Yang 2023-09-26 09:36:54 -07:00
  • 7774ed4ae6 Update README.md for linux + cleanup (#601) Michael Chiang 2023-09-25 23:44:53 -07:00
  • 11f920f209 Merge pull request #599 from jmorganca/mxyng/install.sh Michael Yang 2023-09-25 18:24:13 -07:00
  • 6e6b655956 update install.sh Michael Yang 2023-09-25 18:09:34 -07:00
  • 110ae89a6c Merge pull request #596 from jmorganca/mxyng/install.sh Michael Yang 2023-09-25 17:59:13 -07:00
  • 5e388f931e check cuda installed before installing Michael Yang 2023-09-25 17:56:43 -07:00
  • d5ad41dd7b fix path for wsl user Michael Yang 2023-09-25 17:56:25 -07:00
  • d294a11bc9 start service on exit instead of immediately Michael Yang 2023-09-25 16:11:21 -07:00
  • 93d887e4bc add painter message for exit Michael Yang 2023-09-25 16:30:14 -07:00