Commit graph

2308 commits

Author SHA1 Message Date
Michael Yang
0944b01e7d pull fixes 2023-07-12 09:55:07 -07:00
Jeffrey Morgan
5028de2901 update vicuna model 2023-07-12 09:42:26 -07:00
Michael Yang
e1f0a0dc74 fix eof error in generate 2023-07-12 09:36:16 -07:00
Michael Yang
b227261f21
Merge pull request #71 from jmorganca/llama-errors
error checking new model
2023-07-12 09:20:33 -07:00
Jeffrey Morgan
c63f811909 return error if model fails to load 2023-07-11 20:32:26 -07:00
Jeffrey Morgan
7c71c10d4f fix compilation issue in Dockerfile, remove from README.md until ready 2023-07-11 19:51:08 -07:00
Michael Yang
c5f7eadd87 error checking new model 2023-07-11 17:07:41 -07:00
Jeffrey Morgan
dcb6ba389a app: trim server lines before logging 2023-07-11 16:43:19 -07:00
Jeffrey Morgan
ed6abba75a app: bundle real ggml-metal.metal instead of symlink 2023-07-11 16:36:39 -07:00
Jeffrey Morgan
b52a400cdf use go build on publish 2023-07-11 16:17:45 -07:00
Jeffrey Morgan
2ed26f0047 tweak logging 2023-07-11 16:16:38 -07:00
Jeffrey Morgan
e64ef69e34 look for ggml-metal in the same directory as the binary 2023-07-11 15:58:56 -07:00
Jeffrey Morgan
3d0a9b477b log to console as well as file 2023-07-11 15:52:22 -07:00
Michael Yang
7226980fb6
Merge pull request #70 from jmorganca/offline-fixes
offline fixes
2023-07-11 15:50:19 -07:00
Michael Yang
a806b03f62 no errgroup 2023-07-11 14:58:10 -07:00
Michael Yang
948323fa78 rename partial file 2023-07-11 13:50:26 -07:00
Michael Yang
e243329e2e check api status 2023-07-11 13:42:05 -07:00
Michael Yang
2a66a1164a common stream producer 2023-07-11 13:42:05 -07:00
Michael Yang
62620914e9
Merge pull request #65 from jmorganca/bindings
call llama.cpp directly from go
2023-07-11 12:01:03 -07:00
Michael Yang
442dec1c6f vendor llama.cpp 2023-07-11 11:59:18 -07:00
Michael Yang
fd4792ec56 call llama.cpp directly from go 2023-07-11 11:59:18 -07:00
hoyyeva
abaf7d3bda
Merge pull request #67 from jmorganca/log
writing logs to `./ollama/logs`
2023-07-11 14:45:21 -04:00
Eva Ho
7762584fb1 address comments 2023-07-11 14:38:38 -04:00
Jeffrey Morgan
317615fd5c web: remove unused code 2023-07-11 11:05:45 -07:00
Eva Ho
acc31427dd add logs to ~/.ollama/logs folder 2023-07-11 13:33:32 -04:00
Jeffrey Morgan
a3ec1ec2a0 consistent error handling for pull and generate 2023-07-10 21:34:15 -07:00
Eva Ho
407a5cabf4 when app is running, server restarts when it exits or disconnects 2023-07-10 17:14:25 -04:00
Michael Yang
0859d50942
Merge pull request #58 from jmorganca/generate-errors
return error in generate response
2023-07-10 14:03:47 -07:00
Jeffrey Morgan
66bbf05918 start server in both dev and when packaged 2023-07-10 13:46:31 -07:00
Michael Yang
edba935d67 return error in generate response 2023-07-10 13:30:10 -07:00
Bruce MacDonald
2d49197b3b increase default model size to 512 2023-07-10 21:24:41 +02:00
Bruce MacDonald
f5e2e150b8 allow overriding default generate options 2023-07-10 20:58:02 +02:00
Jeffrey Morgan
268e362fa7 fix binding build 2023-07-10 11:33:43 -07:00
Bruce MacDonald
07a4c1e3fb
take all args as one prompt 2023-07-10 06:05:09 -04:00
Jeffrey Morgan
20dae6b38f add vercel.json to silence PR comments 2023-07-09 20:11:37 -07:00
Jeffrey Morgan
a18e6b3a40 llama: remove unnecessary std::vector 2023-07-09 10:51:45 -04:00
Jeffrey Morgan
5fb96255dc llama: remove unused helper functions 2023-07-09 10:25:07 -04:00
Jeffrey Morgan
b43ddd84be update README.md instructions section 2023-07-08 19:19:31 -04:00
Jeffrey Morgan
993cb9fad6 examples: add basic python example 2023-07-08 17:40:05 -04:00
Jeffrey Morgan
a8dc0c9b5f web: use proper caching for autoupdate endpoint 2023-07-08 16:48:02 -04:00
Jeffrey Morgan
1e97807808 web: revalidate download every minute 2023-07-08 13:45:47 -04:00
Jeffrey Morgan
840f87430a remove double heartbeat 2023-07-08 13:30:27 -04:00
Jeffrey Morgan
660dee7005 hourly heartbeat 2023-07-08 13:18:34 -04:00
Jeffrey Morgan
a678a7235a shorter README.md 2023-07-07 23:54:50 -04:00
Jeffrey Morgan
74e92d1258 add basic / route for server 2023-07-07 23:46:15 -04:00
Jeffrey Morgan
ea809df196 update Dockerfile to use OLLAMA_HOST 2023-07-07 23:43:50 -04:00
Bruce MacDonald
0bee4a8c07
if directory cannot be resolved, do not fail 2023-07-07 23:18:25 -04:00
Bruce MacDonald
f533f85d44 pr feedback
- move error check to api client pull
- simplify error check in generate
- return nil on any pull error
2023-07-07 17:12:02 -04:00
Jeffrey Morgan
553c884474 allow specifying server host and port with OLLAMA_HOST and OLLAMA_PORT 2023-07-07 16:48:13 -04:00
Jeffrey Morgan
b245f5af8f web:open download page in new tab 2023-07-07 16:29:58 -04:00