Jeremy
70261b9bb6
move static build to its own flag
2024-04-17 13:04:28 -04:00
Blake Mizerany
9df6c85c3a
types/model: add FilepathNoBuild ( #3680 )
...
Also, add test for DisplayLongest.
Also, plumb fill param to ParseName in MustParseName
2024-04-16 18:35:43 -07:00
Michael Yang
fb9580df85
Merge pull request #3684 from ollama/mxyng/scale-graph
...
scale graph based on gpu count
2024-04-16 14:57:09 -07:00
Michael Yang
26df674785
scale graph based on gpu count
2024-04-16 14:44:13 -07:00
Jeffrey Morgan
7c9792a6e0
Support unicode characters in model path ( #3681 )
...
* parse wide argv characters on windows
* cleanup
* move cleanup to end of `main`
2024-04-16 17:00:12 -04:00
Michael Yang
7afb2e125a
Merge pull request #3678 from ollama/mxyng/fix-darwin-partial-offloading
...
darwin: no partial offloading if required memory greater than system
2024-04-16 12:05:56 -07:00
Michael Yang
41a272de9f
darwin: no partial offloading if required memory greater than system
2024-04-16 11:22:38 -07:00
Jeffrey Morgan
f335722275
update llama.cpp submodule to 7593639 ( #3665 )
2024-04-15 23:04:43 -04:00
Michael Yang
6d53b67c2c
Merge pull request #3663 from ollama/mxyng/fix-padding
2024-04-15 17:44:54 -07:00
Michael Yang
969238b19e
fix padding in decode
...
TODO: update padding() to _only_ returning the padding
2024-04-15 17:27:06 -07:00
Blake Mizerany
949d7832cf
Revert "cmd: provide feedback if OLLAMA_MODELS is set on non-serve command ( #3470 )" ( #3662 )
...
This reverts commit 7d05a6ee8fhttps://github.com/ollama/ollama/issues/3624
2024-04-15 16:58:00 -07:00
Sung Kim
99d227c9db
Added Solar example at README.md ( #3610 )
...
Added just one line
| Solar | 10.7B | 6.1GB | `ollama run solar` |
2024-04-15 19:54:23 -04:00
Carlos Gamez
a27e419b47
Update langchainjs.md ( #2030 )
...
Changed ollama.call() for ollama.invoke() as per deprecated documentation from langchain
2024-04-15 18:37:30 -04:00
Chandre Van Der Westhuizen
e4d0db5a97
Added MindsDB information ( #3595 )
...
* Added MindsDB information
Added more details to MindsDB so that Ollama users can know that they can connect their Ollama model with 200+ databases and apps
* updated text for mindsdb
2024-04-15 18:35:29 -04:00
Eli Bendersky
ba460802c2
examples: add more Go examples using the API ( #3599 )
...
* examples: go-multimodal
* examples: add go-pull-progress
* examples: add go-chat
* fix
2024-04-15 18:34:54 -04:00
Jeffrey Morgan
e54a3c7fcd
Update modelfile.md
...
Remove Modelfile parameters that are decided at runtime
2024-04-15 15:35:44 -04:00
Patrick Devine
9f8691c6c8
Add llama2 / torch models for ollama create ( #3607 )
2024-04-15 11:26:42 -07:00
Jeffrey Morgan
a0b8a32eb4
Terminate subprocess if receiving SIGINT or SIGTERM signals while model is loading ( #3653 )
...
* terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading
* use `unload` in signal handler
2024-04-15 12:09:32 -04:00
Jeffrey Morgan
7027f264fb
app: gracefully shut down ollama serve on windows ( #3641 )
...
* app: gracefully shut down `ollama serve` on windows
* fix linter errors
* bring back `HideWindow`
* remove creation flags
* restore `windows.CREATE_NEW_PROCESS_GROUP`
2024-04-14 18:33:25 -04:00
Blake Mizerany
9bee3b63b1
types/model: add path helpers ( #3619 )
...
This commit adds path helpers for working with Names in URL and file
paths. The new helpers are ParseNameFromPath, ParseNameFromFilePath,
Name.Path, and Name.FilePath.
This commit also adds Name.DisplayLongest, and Name.DisplayLong.
Also, be it updates a place where strings.StripPrefix is more consistent
with the surrounding code.
Also, replace Parts with specific methods
2024-04-13 12:59:19 -07:00
Jeffrey Morgan
309aef7fee
update llama.cpp submodule to 4bd0f93 ( #3627 )
2024-04-13 10:43:02 -07:00
Blake Mizerany
08655170aa
types/model: make ParseName variants less confusing ( #3617 )
...
Also, fix http stripping bug.
Also, improve upon docs about fills and masks.
2024-04-12 13:57:57 -07:00
Blake Mizerany
2b341069a7
types/model: remove (*Digest).Scan and Digest.Value ( #3605 )
2024-04-11 13:32:31 -07:00
Daniel Hiltgen
c00fee6936
Merge pull request #3604 from dhiltgen/fix_rocm_deps
...
Fix rocm deps with new subprocess paths
2024-04-11 13:08:29 -07:00
Daniel Hiltgen
c2d813bdc3
Fix rocm deps with new subprocess paths
2024-04-11 12:52:06 -07:00
Michael Yang
786f3a1c44
Merge pull request #3600 from ollama/mxyng/mixtral
2024-04-11 12:23:37 -07:00
Michael Yang
3397eff0cd
mixtral mem
2024-04-11 11:10:41 -07:00
Blake Mizerany
0efb7931c7
Revert "types/model: remove (*Digest).Scan and Digest.Value ( #3589 )"
...
This reverts commit 42f2cc408e
2024-04-11 00:45:07 -07:00
Blake Mizerany
42f2cc408e
types/model: remove (*Digest).Scan and Digest.Value ( #3589 )
2024-04-11 00:37:26 -07:00
Blake Mizerany
9446b795b5
types/model: remove DisplayLong ( #3587 )
2024-04-10 16:55:12 -07:00
Blake Mizerany
62f8cda3b3
types/model: remove MarshalText/UnmarshalText from Digest ( #3586 )
2024-04-10 16:52:49 -07:00
Blake Mizerany
6a1de23175
types/model: init with Name and Digest types ( #3541 )
2024-04-10 16:30:05 -07:00
Blake Mizerany
a7b431e743
server: provide helpful workaround hint when stalling on pull ( #3584 )
...
This is a quick fix to help users who are stuck on the "pull" step at
99%.
In the near future we're introducing a new registry client that
should/will hopefully be smarter. In the meantime, this should unblock
the users hitting issue #1736 .
2024-04-10 16:24:37 -07:00
Michael Yang
5a25f93522
Merge pull request #3478 from ollama/mxyng/tensor-layer
...
refactor tensor query
2024-04-10 12:45:03 -07:00
Michael Yang
7e33a017c0
partial offloading
2024-04-10 11:37:20 -07:00
Michael Yang
8b2c10061c
refactor tensor query
2024-04-10 11:37:20 -07:00
Michael Yang
c5c451ca3b
Merge pull request #3579 from ollama/mxyng/fix-ci
...
fix ci
2024-04-10 11:37:01 -07:00
Michael Yang
2b4ca6cf36
fix ci
2024-04-10 11:35:12 -07:00
Eli Bendersky
ad90b9ab3d
api: start adding documentation to package api ( #2878 )
...
* api: start adding documentation to package api
Updates #2840
* Fix lint typo report
2024-04-10 13:31:55 -04:00
Eli Bendersky
4340f8eba4
examples: start adding Go examples using api/ ( #2879 )
...
We can have the same examples as e.g. https://github.com/ollama/ollama-python/tree/main/examples
here. Using consistent naming and renaming the existing example to have -http-
since it uses direct HTTP requests rather than api/
Updates #2840
2024-04-10 13:26:45 -04:00
Daniel Hiltgen
4c7db6b7e9
Merge pull request #3566 from dhiltgen/more_time
...
Handle very slow model loads
2024-04-09 16:53:49 -07:00
Michael Yang
c03f0e3c3d
Merge pull request #3565 from ollama/mxyng/rope
...
fix: rope
2024-04-09 16:36:55 -07:00
Daniel Hiltgen
c5ff443b9f
Handle very slow model loads
...
During testing, we're seeing some models take over 3 minutes.
2024-04-09 16:35:10 -07:00
Michael Yang
01114b4526
fix: rope
2024-04-09 16:15:24 -07:00
Blake Mizerany
1524f323a3
Revert "build.go: introduce a friendlier way to build Ollama ( #3548 )" ( #3564 )
2024-04-09 15:57:45 -07:00
Blake Mizerany
fccf3eecaa
build.go: introduce a friendlier way to build Ollama ( #3548 )
...
This commit introduces a more friendly way to build Ollama dependencies
and the binary without abusing `go generate` and removing the
unnecessary extra steps it brings with it.
This script also provides nicer feedback to the user about what is
happening during the build process.
At the end, it prints a helpful message to the user about what to do
next (e.g. run the new local Ollama).
2024-04-09 14:18:47 -07:00
Michael Yang
c77d45d836
Merge pull request #3506 from ollama/mxyng/quantize-redux
...
cgo quantize
2024-04-09 12:32:53 -07:00
Jeffrey Morgan
5ec12cec6c
update llama.cpp submodule to 1b67731 ( #3561 )
2024-04-09 15:10:17 -04:00
Michael Yang
d9578d2bad
Merge pull request #3559 from ollama/mxyng/ci
...
ci: use go-version-file
2024-04-09 11:03:18 -07:00
Michael Yang
cb8352d6b4
ci: use go-version-file
2024-04-09 09:50:12 -07:00
