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

Commit graph

  • 041f9ad1a1 update README.md Michael Yang 2023-08-25 11:44:25 -0700
  • 7a378f8b66 patch llama.cpp for 34B Michael Yang 2023-08-25 10:06:55 -0700
  • de0bdd7f29
         Merge pull request #405 from jmorganca/mxyng/34b Michael Yang 2023-08-24 10:37:22 -0700
  • b1cececb8e add 34b model type Michael Yang 2023-08-24 10:35:44 -0700
  • e0d39fa3bf
         Merge pull request #398 from jmorganca/mxyng/cleanup Michael Yang 2023-08-22 15:51:41 -0700
  • 968ced2e71
         Merge pull request #393 from jmorganca/mxyng/net-url Michael Yang 2023-08-22 15:51:33 -0700
  • 32d1a00017 remove unused requestContextKey Michael Yang 2023-08-22 08:51:21 -0700
  • 04e2128273 move upload funcs to upload.go Michael Yang 2023-08-22 08:50:21 -0700
  • 2cc634689b use url.URL Michael Yang 2023-08-21 18:38:31 -0700
  • 8f827641b0
         Merge pull request #397 from jmorganca/mxyng/release-mode Michael Yang 2023-08-22 10:48:44 -0700
  • 95187d7e1e build release mode Michael Yang 2023-08-22 09:48:35 -0700
  • 9ec7e37534
         Merge pull request #392 from jmorganca/mxyng/version Michael Yang 2023-08-22 09:50:25 -0700
  • 2c7f956b38 add version Michael Yang 2023-08-21 18:24:42 -0700
  • a9f6c56652 fix FROM instruction erroring when referring to a file Jeffrey Morgan 2023-08-22 09:39:42 -0700
  • 0a892419ad
         Strip protocol from model path (#377) Ryan Baker 2023-08-21 21:56:56 -0700
  • e3054fc74e add .env to .dockerignore Jeffrey Morgan 2023-08-21 09:32:02 -0700
  • 23c2485044
         Merge pull request #381 from jmorganca/mxyng/fix-push-chunks Michael Yang 2023-08-18 13:49:25 -0700
  • 386c66f285
         Merge pull request #378 from jmorganca/mxyng/copy-metadata-from-source Michael Yang 2023-08-18 13:49:09 -0700
  • 3b49315f97 retry on unauthorized chunk push Michael Yang 2023-08-18 10:03:29 -0700
  • 5ca05c2e88 fix ModelType() Michael Yang 2023-08-18 11:23:31 -0700
  • 7eda70f23b copy metadata from source Michael Yang 2023-08-17 21:52:11 -0700
  • 3d79b414d3 app: package ggml-metal.metal from correct directory Jeffrey Morgan 2023-08-17 23:55:45 -0400
  • c84bbf1dd6
         Merge pull request #376 from jmorganca/mxyng/from-map-ignore-nil Michael Yang 2023-08-17 15:57:12 -0700
  • f723bf0879 ignore nil map values Michael Yang 2023-08-17 15:50:46 -0700
  • cbf725a9ba
         Merge pull request #375 from jmorganca/mxyng/fix-push Michael Yang 2023-08-17 15:33:31 -0700
  • 086449b6c7 fmt Michael Yang 2023-08-17 15:32:31 -0700
  • 3cbc6a5c01 fix push manifest Michael Yang 2023-08-17 12:35:29 -0700
  • 54bb49a502 parse protocol for OLLAMA_HOST Jeffrey Morgan 2023-08-17 18:20:38 -0400
  • cabaada956
         Merge pull request #372 from jmorganca/mxyng/string-types Michael Yang 2023-08-17 15:10:59 -0700
  • a894cc792d model and file type as strings Michael Yang 2023-08-17 11:37:27 -0700
  • 519f4d98ef
         add embed docs for modelfile Bruce MacDonald 2023-08-17 13:37:42 -0400
  • b963a83559
         Merge pull request #364 from jmorganca/chunked-uploads Michael Yang 2023-08-17 09:58:51 -0700
  • bf6688abe6
         Merge pull request #360 from jmorganca/fix-request-copies Michael Yang 2023-08-17 09:58:42 -0700
  • 6005b157c2
         retry download on network errors Bruce MacDonald 2023-08-17 10:31:45 -0400
  • 14220d9833
         set the scopes correctly (#368) Patrick Devine 2023-08-16 21:42:02 -0700
  • 8ca50f24f3
         fix nous-hermes model file size listing in readme (#367) Michael Chiang 2023-08-16 23:42:00 -0400
  • c149fc3143
         Update README.md Michael Chiang 2023-08-16 22:54:55 -0400
  • afbc763dac
         adding link to models directly available on ollama (#366) Michael Chiang 2023-08-16 22:53:27 -0400
  • 5dfe91be8b reimplement chunked uploads Michael Yang 2023-08-14 17:50:06 -0700
  • 9f944c00f1 push: retry on unauthorized Michael Yang 2023-08-16 11:12:24 -0700
  • 56e87cecb1 images: remove body copies Michael Yang 2023-08-16 10:30:41 -0700
  • 5ee6116420 set default OLLAMA_HOST to http://localhost:11434 Jeffrey Morgan 2023-08-16 12:22:59 -0400
  • 5d9a4cd251
         Merge pull request #348 from jmorganca/cross-repo-mount Michael Yang 2023-08-16 09:20:36 -0700
  • 0ebec07569
         Merge pull request #345 from jmorganca/exit-non-zero Michael Yang 2023-08-16 09:20:28 -0700
  • 08265515b3
         Merge pull request #303 from jmorganca/matt/dockerit Matt Williams 2023-08-16 08:04:34 -0700
  • 67e593e355
         cmd: support OLLAMA_CLIENT_HOST environment variable (#262) Blake Mizerany 2023-08-16 08:03:48 -0700
  • d15c7622b9 Update orca to orca-mini in README.md Jeffrey Morgan 2023-08-15 21:10:28 -0400
  • 1deb35ca64
         use loaded llm for generating model file embeddings Bruce MacDonald 2023-08-15 16:12:02 -0300
  • e2de886831
         do not regenerate embeddings Bruce MacDonald 2023-08-15 16:10:22 -0300
  • f0d7c2f5ea retry download on network errors Bruce MacDonald 2023-08-15 15:07:19 -0300
  • 12052a7624
         always remove from in progress map on download Bruce MacDonald 2023-08-15 13:20:32 -0300
  • 23e1da778d
         Add context to api docs Bruce MacDonald 2023-08-15 11:43:22 -0300
  • 326de48930 use loaded llm for embeddings Bruce MacDonald 2023-08-15 10:35:39 -0300
  • 18f2cb0472 dont log fatal Bruce MacDonald 2023-08-15 10:39:59 -0300
  • 53bc36d207
         Update modelfile.md Bruce MacDonald 2023-08-15 09:23:36 -0300
  • 4dcf5c3e0b
         Merge pull request #349 from jmorganca/close-files Michael Yang 2023-08-14 16:15:58 -0700
  • d1b2f532b9
         Merge pull request #350 from jmorganca/update-llama-cpp Michael Yang 2023-08-14 16:15:51 -0700
  • e26085b921 close open files Michael Yang 2023-08-14 16:08:02 -0700
  • f7b613332c update llama.cpp Michael Yang 2023-08-14 15:47:00 -0700
  • f594c8eb91 cross repo mount Michael Yang 2023-08-14 15:07:00 -0700
  • 76b85bc0e9 set non-zero error code on error Michael Yang 2023-08-14 11:15:53 -0700
  • af98a1773f update python example Bruce MacDonald 2023-08-14 16:38:44 -0300
  • 9ae9a89883 Update modelfile.md Bruce MacDonald 2023-08-14 16:26:53 -0300
  • 648f0974c6 python example Bruce MacDonald 2023-08-14 15:27:13 -0300
  • fc5230dffa
         Add context to api docs Bruce MacDonald 2023-08-14 15:23:24 -0300
  • 2ab20095b3
         log embedding eval timing Bruce MacDonald 2023-08-14 12:15:55 -0400
  • f020e1d519 always remove from in progress map on download Bruce MacDonald 2023-08-14 13:09:20 -0300
  • 4b2d366c37 Update llama.go Bruce MacDonald 2023-08-14 12:55:50 -0300
  • 56fd4e4ef2 log embedding eval timing Bruce MacDonald 2023-08-14 12:51:31 -0300
  • 2c8b680b03 use file info for embeddings cache Bruce MacDonald 2023-08-14 12:11:04 -0300
  • 99b6b60085 use model bin digest for embed digest Bruce MacDonald 2023-08-14 11:57:12 -0300
  • 74f00474e1
         Merge pull request #340 from gusanmaz/main Bruce MacDonald 2023-08-14 09:38:42 -0400
  • e9a9580bdd do not regenerate embeddings Bruce MacDonald 2023-08-14 10:34:17 -0300
  • 4c33a9ac67
         Update langchainpy.md Güvenç Usanmaz 2023-08-14 12:12:56 +0300
  • 22885aeaee update llama.cpp to f64d44a Jeffrey Morgan 2023-08-12 22:47:15 -0400
  • ed969d2a06 add LiteLLM to README.md Jeffrey Morgan 2023-08-12 20:47:53 -0400
  • d9cf18e28d
         add maximum retries when pushing (#334) Patrick Devine 2023-08-11 15:41:55 -0700
  • 1556162c90 create .ollama directory if it doesnt exist Jeffrey Morgan 2023-08-11 15:35:55 -0700
  • 148f0225c0 create .ollama directory if it doesnt exist Jeffrey Morgan 2023-08-11 15:33:11 -0700
  • 4e07941b1e
         Merge pull request #329 from jmorganca/matt/tutorials Matt Williams 2023-08-11 15:19:39 -0700
  • 202c29c21a resolving bmacd comment Matt Williams 2023-08-11 13:51:44 -0700
  • c1c871620a
         Update docs/tutorials/langchainjs.md Matt Williams 2023-08-11 13:48:46 -0700
  • a21a8bef56
         Update docs/tutorials/langchainjs.md Matt Williams 2023-08-11 13:48:35 -0700
  • 522726228a
         Update docs/tutorials.md Matt Williams 2023-08-11 13:48:16 -0700
  • 9770e3b325
         Generate private/public keypair for use w/ auth (#324) Patrick Devine 2023-08-11 10:58:23 -0700
  • d617823355
         Merge pull request #333 from jmorganca/off-by-one Michael Yang 2023-08-11 10:51:06 -0700
  • 6ed991c8e2 ggml: fix off by one error Michael Yang 2023-08-11 10:45:19 -0700
  • e41576e768 Merge branch 'new-syntax' of https://github.com/jmorganca/ollama into new-syntax Michael Chiang 2023-08-11 09:00:43 -0700
  • 155c1640f1 add demo video Michael Chiang 2023-08-11 08:58:57 -0700
  • f7d4947573 update header note for privategpt example Jeffrey Morgan 2023-08-11 08:52:26 -0700
  • 0d7a133b15 Update README.md for privategpt Jeffrey Morgan 2023-08-11 08:29:19 -0700
  • e863066144 clean up privategpt example Jeffrey Morgan 2023-08-11 00:34:52 -0700
  • 89a92477ad fix README.md for privategpt example Jeffrey Morgan 2023-08-11 00:26:33 -0700
  • 5cda9cdd13 add instructions to privategpt example to try another model Jeffrey Morgan 2023-08-11 00:23:31 -0700
  • e5914eb320 add venv instructions to privategpt example Jeffrey Morgan 2023-08-11 00:20:22 -0700
  • ab78f48ff8 more setup instructions for privategpt example Jeffrey Morgan 2023-08-11 00:19:25 -0700
  • b1c88eb978 add privategpt example Jeffrey Morgan 2023-08-11 00:18:13 -0700
  • efae43f932 update langchain examples Jeffrey Morgan 2023-08-10 23:35:19 -0700
  • d3ee1329e9 Add tutorials for using Langchain with ollama Matt Williams 2023-08-10 21:27:37 -0700
  • 700c719422 remove document example for now Jeffrey Morgan 2023-08-10 20:25:01 -0700