Jesse Gross
97ec8cfd4e
image: Clarify argument to WriteManifest is config
...
When creating a model the config layer is appended to the list of
layers and then the last layer is used as the config when writing the
manifest. This change directly uses the config layer to write the
manifest. There is no behavior change but it is less error prone.
2024-08-07 16:58:42 -07:00
royjhan
5b3a21b578
add metrics to docs ( #6079 )
2024-08-07 14:43:44 -07:00
Kyle Kelley
ad0c19dde4
Use llama3.1 in tools example ( #5985 )
...
* Use llama3.1 in tools example
* Update api.md
2024-08-07 17:20:50 -04:00
Jesse Gross
69eb06c40e
Merge pull request #6145 from ollama/jessegross/bug5840
...
Fix crash on startup when trying to clean up unused files (#5840 )
2024-08-07 11:24:15 -07:00
Jesse Gross
1829fb61bd
manifest: Fix crash on startup when trying to clean up unused files ( #5840 )
...
Currently if the config field is missing in the manifest file (or
corrupted), Ollama will crash when it tries to read it. This can
happen at startup or when pulling new models.
This data is mostly just used for showing model information so we
can be tolerant of it not being present - it is not required to
run the models. Besides avoiding crashing, this also gives us the
ability to restructure the config in the future by pulling it
into the main manifest file.
2024-08-07 10:30:44 -07:00
Jesse Gross
685a53534b
manifest: Don't prune layers if we can't open a manifest file
...
If there is an error when opening a manifest file (corrupted, permission denied, etc.)
then the referenced layers will not be included in the list of active
layers. This causes them to be deleted when pruning happens at startup
or a model is pulled.
In such a situation, we should prefer to preserve data in the hopes that
it can be recovered rather than being agressive about deletion.
2024-08-06 23:11:19 -07:00
Jeffrey Morgan
de4fc29773
llm: reserve required number of slots for embeddings ( #6219 )
2024-08-06 23:20:49 -04:00
Jeffrey Morgan
e04c7012c2
update llama.cpp submodule to 1e6f6554 ( #6208 )
2024-08-06 15:11:45 -04:00
Chua Chee Seng
d4a7216c82
Fixed invalid option provided not displaying the invalid option name problem. ( #6202 )
2024-08-06 14:37:16 -04:00
Daniel Hiltgen
a4fdd03c3b
Merge pull request #6207 from dhiltgen/sparse_win
...
Ensure sparse files on windows during download
2024-08-06 11:06:06 -07:00
Daniel Hiltgen
fc85f50a2b
Ensure sparse files on windows during download
...
The file.Truncate call on windows will write the whole file
unless you set the sparse flag, leading to heavy I/O at the
beginning of download. This should improve our
I/O behavior on windows and put less stress on the users disk.
2024-08-06 10:58:08 -07:00
royjhan
86b907f82a
sort batch results ( #6189 )
2024-08-05 16:55:34 -07:00
Michael Yang
10d49bce70
Merge pull request #6190 from ollama/mxyng/fix-integration
...
fix concurrency test
2024-08-05 16:45:49 -07:00
Michael Yang
7ed367419e
fix concurrency test
2024-08-05 16:36:16 -07:00
Daniel Hiltgen
50ee8b5f56
Merge pull request #6186 from dhiltgen/numa
...
Implement linux NUMA detection
2024-08-05 15:20:06 -07:00
Michael Yang
03bdac0595
Merge pull request #6146 from ollama/mxyng/testing
...
use testing tempdirs
2024-08-05 13:00:05 -07:00
Daniel Hiltgen
f457d63400
Implement linux NUMA detection
...
If the system has multiple numa nodes, enable numa support in llama.cpp
If we detect numactl in the path, use that, else use the basic "distribute" mode.
2024-08-05 12:56:20 -07:00
Michael Yang
39f2bc6bfc
Merge pull request #6167 from ollama/mxyng/line-feed
...
line feed
2024-08-05 00:06:28 -07:00
frob
b73b0940ef
Disable paging for journalctl ( #6154 )
...
Users using `journalctl` to get logs for issue logging sometimes don't realize that paging is causing information to be missed.
2024-08-05 00:10:53 -04:00
Michael Yang
6a07344786
line feed
2024-08-04 17:25:41 -07:00
sryu1
8b920f35a4
Add Gemma 2 2b ( #6151 )
2024-08-04 10:58:39 -04:00
Ivan Charapanau
4221e39867
Reference ollama integration with Harbor ( #6147 )
2024-08-02 17:03:46 -07:00
Michael Yang
a091fadfda
use testing tempdirs
2024-08-02 16:04:06 -07:00
Michael Yang
77ccbf04dc
Merge pull request #6128 from ollama/mxyng/lint
...
enable gofmt/gofumpt/goimports/tenv
2024-08-02 14:58:40 -07:00
royjhan
4addf6b587
Update OpenAI Compatibility Docs with /v1/completions ( #5311 )
...
* Update docs
* token bug corrected
* Update docs/openai.md
* Update docs/openai.md
* add suffix
* merge conflicts
* merge conflicts
2024-08-02 13:16:23 -07:00
royjhan
85c7f11170
Update docs ( #5310 )
2024-08-02 13:05:57 -07:00
Michael Yang
b732beba6a
lint
2024-08-01 17:06:06 -07:00
Kim Hallberg
ce1fb4447e
Fix models/{model} URL ( #6132 )
2024-08-01 16:31:47 -07:00
royjhan
558a54b098
Update OpenAI Compatibility Docs with /v1/embeddings ( #5470 )
...
* docs without usage
* no usage
* rm metric note
2024-08-01 16:00:29 -07:00
royjhan
ed52833bb1
Add to docs ( #5309 )
2024-08-01 15:58:13 -07:00
royjhan
6f133a0bdd
OpenAI: Add Usage to v1/embeddings ( #5886 )
...
* add prompt tokens to embed response
* rm slog
* metrics
* types
* prompt n
* clean up
* reset submodule
* add tokens to v1/embeddings
* separate usage
2024-08-01 15:49:37 -07:00
royjhan
f561eecfb8
Update OpenAI Compatibility Docs with /v1/models ( #5151 )
...
* OpenAI Docs
* Update docs/openai.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
* Remove newline
---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-08-01 15:48:44 -07:00
Michael Yang
ff7c9060ec
Merge pull request #6115 from slouffka/fix-context
...
Fix context in /api/generate grows too much (#5980 ).
2024-08-01 15:13:59 -07:00
Michael Yang
0ff42e84b0
Merge pull request #4756 from ollama/mxyng/convert2
...
refactor convert
2024-08-01 14:16:30 -07:00
Vyacheslav Moskalev
8a9f946ca7
Refactor and format code.
2024-08-02 03:50:05 +07:00
Vyacheslav Moskalev
3b5210548e
Refactor code. Remove extra variable.
2024-08-01 19:56:15 +07:00
Vyacheslav Moskalev
b0c216584c
Better types and naming closer to style.
2024-08-01 19:43:44 +07:00
Vyacheslav Moskalev
49a5483139
Change the order of context and prompt.
2024-08-01 19:25:56 +07:00
Vyacheslav Moskalev
6bc5c13758
Fix extra context concatenation in generate handler ( #5980 ).
2024-08-01 15:45:58 +07:00
Michael Yang
3e614260af
Merge pull request #6109 from ollama/mxyng/fix-modelfile
...
fix modelfile message quotes
2024-07-31 17:05:43 -07:00
Michael Yang
d87b4a488e
fix modelfile message quotes
2024-07-31 16:52:09 -07:00
Michael Yang
4c14855ad7
Merge pull request #6106 from ollama/mxyng/default-sliding-window-attention
...
patches: phi3 optional sliding window attention
2024-07-31 16:12:06 -07:00
Blake Mizerany
dc77bbcfa4
server: fix json marshalling of downloadBlobPart ( #6108 )
2024-07-31 16:01:24 -07:00
Michael Yang
d8e2664c33
convert: fix parse functions
2024-07-31 15:58:55 -07:00
Michael Yang
eafc607abb
convert: only extract large files
2024-07-31 15:58:55 -07:00
Michael Yang
781fc2d576
Update convert/reader_safetensors.go
...
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-07-31 15:58:55 -07:00
Michael Yang
df993fa37b
comments
2024-07-31 15:58:55 -07:00
Michael Yang
5e9db9fb0b
refactor convert
2024-07-31 15:58:33 -07:00
Michael Yang
0f3271db88
patches: phi3 default sliding window attention
2024-07-31 14:58:34 -07:00
Michael Yang
6b252918fb
update convert test to check result data
2024-07-31 10:59:38 -07:00
