Commit graph

3501 commits

Author SHA1 Message Date
Richard Lyons
885cf45087 Fix white space. 2024-08-18 03:07:16 +02:00
Richard Lyons
9352eeb752 Reset NumCtx. 2024-08-18 02:55:01 +02:00
Richard Lyons
0ad0e738cd Override numParallel only if unset. 2024-08-18 01:43:26 +02:00
zwwhdls
bdc4308afb fix: chmod new layer to 0o644 when creating it
Signed-off-by: zwwhdls <zww@hdls.me>
2024-08-16 11:43:19 +08:00
Daniel Hiltgen
d29cd4c2ed
Merge pull request #6381 from eust-w/main
fix: Add tooltip to system tray icon
2024-08-15 15:31:15 -07:00
eust-w
a84c05cf91 fix: Add tooltip to system tray icon
- Updated setIcon method to include tooltip text for the system tray icon.
- Added NIF_TIP flag and set the tooltip text using UTF16 encoding.

Resolves: #6372
2024-08-16 06:00:12 +08:00
Michael Yang
e3d7f32af7
Merge pull request #6363 from ollama/mxyng/fix-noprune
fix: noprune on pull
2024-08-15 12:20:38 -07:00
Michael Yang
3a75e74e34 only skip invalid json manifests 2024-08-15 10:29:14 -07:00
Michael Yang
237dccba1e skip invalid manifest files 2024-08-14 16:55:45 -07:00
Michael Yang
b3f75fc812 fix noprune 2024-08-14 15:48:51 -07:00
Jeffrey Morgan
8200c371ae
add CONTRIBUTING.md (#6349) 2024-08-14 15:19:50 -07:00
longtao
0a8d6ea86d
Fix typo and improve readability (#5964)
* Fix typo and improve readability

Summary:
* Rename updatAvailableMenuID to updateAvailableMenuID
* Replace unused cmd parameter with _ in RunServer function
* Fix typos in comments

(cherry picked from commit 5b8715f0b04773369e8eb1f9e6737995a0ab3ba7)

* Update api/client.go

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

---------

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2024-08-13 17:54:19 -07:00
Blake Mizerany
8e1050f366
server: reduce max connections used in download (#6347)
The previous value of 64 was WAY too high and unnecessary. It reached
diminishing returns and blew past it. This is a more reasonable number
for _most_ normal cases. For users on cloud servers with excellent
network quality, this will keep screaming for them, without hitting our
CDN limits. For users with relatively poor network quality, this will
keep them from saturating their network and causing other issues.
2024-08-13 16:47:35 -07:00
Bruce MacDonald
eda8a32a09
update chatml template format to latest in docs (#6344) 2024-08-13 16:39:18 -07:00
Michael Yang
a0a40aa20c
Merge pull request #6346 from ollama/mxyng/lint 2024-08-13 14:58:35 -07:00
Michael Yang
2697d7f5aa lint
- fixes printf: non-constant format string in call to fmt.Printf
- fixes SA1032: arguments have the wrong order
- disables testifylint
2024-08-13 14:36:33 -07:00
Pamela Fox
1f32276178
Update openai.md to remove extra checkbox (#6345) 2024-08-13 13:36:05 -07:00
Daniel Hiltgen
4c4fe3f87f
Merge pull request #6343 from dhiltgen/revert_win_go_version
Go back to a pinned Go version
2024-08-13 11:53:49 -07:00
Daniel Hiltgen
feedf49c71 Go back to a pinned Go version
Go version 1.22.6 is triggering AV false positives, so go back to 1.22.5
2024-08-13 11:45:44 -07:00
royjhan
8b00a415ab
Load Embedding Model on Empty Input (#6325)
* load on empty input

* no load on invalid input
2024-08-13 10:19:56 -07:00
Michael Yang
01b80e9ffc
Merge pull request #5443 from ollama/mxyng/convert-phi3
add conversion for microsoft phi 3 mini/medium 4k, 128k
2024-08-12 15:47:58 -07:00
Michael Yang
bd5e432630 update import.md 2024-08-12 15:13:29 -07:00
Bruce MacDonald
aec77d6a05 support new "longrope" attention factor 2024-08-12 15:13:29 -07:00
Michael Yang
6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128 2024-08-12 15:13:29 -07:00
Josh
f7e3b9190f
cmd: spinner progress for transfer model data (#6100) 2024-08-12 11:46:32 -07:00
Josh
980dd15f81
cmd: speed up gguf creates (#6324) 2024-08-12 11:46:09 -07:00
royjhan
01d544d373
OpenAI: Simplify input output in testing (#5858)
* simplify input output

* direct comp

* in line image

* rm error pointer type

* update response testing

* lint
2024-08-12 10:33:34 -07:00
Josh
1dc3ef3aa9
Revert "server: speed up single gguf creates (#5898)" (#6323)
This reverts commit 8aac22438e.
2024-08-12 09:57:51 -07:00
Josh
8aac22438e
server: speed up single gguf creates (#5898) 2024-08-12 09:28:55 -07:00
Jeffrey Morgan
15c2d8fe14
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
For simplicity, perform parallelization of embedding requests in the API handler instead of offloading this to the subprocess runner. This keeps the scheduling story simpler as it builds on existing parallel requests, similar to existing text completion functionality.
2024-08-11 11:57:10 -07:00
Daniel Hiltgen
25906d72d1
llm: prevent loading too large models on windows (#5926)
Don't allow loading models that would lead to memory exhaustion (across vram, system memory and disk paging). This check was already applied on Linux but should also be applied on Windows as well.
2024-08-11 11:30:20 -07:00
CognitiveTech
023451ce47
add integration obook-summary (#6305) 2024-08-10 18:43:08 -07:00
Jesse Gross
9b53e39d8e
Merge pull request #6258 from coolljt0725/fix_typo
server/download.go: Fix a typo in log
2024-08-09 17:19:48 -07:00
Michael Yang
97fae2df95
Merge pull request #6235 from Nicholas42/fix_line_endings
Set *.png and *.ico to be treated as binary files.
2024-08-09 17:06:30 -07:00
Michael Yang
160d9d4900
Merge pull request #6171 from ollama/mxyng/remove-temp
removeall to remove non-empty temp dirs
2024-08-09 15:47:13 -07:00
Nicholas Schwab
d4e6407464 Restrict text files with explicit line feeds to *.go.
This partially reverts b732beba6a. It
seems like explicitly setting all files to use line feeds was done due
to issues with the go linter, hence it can be restricted to those files
(https://github.com/ollama/ollama/pull/6235#issuecomment-2278745953).
2024-08-09 23:14:13 +02:00
Daniel Hiltgen
b7f7d8cd15
Merge pull request #6291 from dhiltgen/no_sparse_fail
Don't hard fail on sparse setup error
2024-08-09 12:30:25 -07:00
Daniel Hiltgen
2fa1db4345 Don't hard fail on sparse setup error
It seems this can fail in some casees, but proceed
with the download anyway.
2024-08-09 12:16:19 -07:00
Daniel Hiltgen
71b0945fc6
Merge pull request #6290 from dhiltgen/intel_npe
Harden intel boostrap for nil pointers
2024-08-09 12:14:42 -07:00
Daniel Hiltgen
5bca2e60a7 Harden intel boostrap for nil pointers 2024-08-09 11:31:38 -07:00
Nicholas42
67472e0e89
Also flag *.icns as binary 2024-08-09 13:41:20 +02:00
Daniel Hiltgen
e9aa5117c4
Merge pull request #6133 from dhiltgen/cuda_repo
Adjust arm cuda repo paths
2024-08-08 12:33:35 -07:00
Daniel Hiltgen
2473bdba5e
Merge pull request #6182 from dhiltgen/more_patterns
Catch one more error log
2024-08-08 12:33:17 -07:00
Michael Yang
2003d60159 llama3.1 memory 2024-08-08 11:18:13 -07:00
Jesse Gross
7d1c0047fa
Merge pull request #6247 from ollama/jessegross/layers
Store layers inside manifests consistently as values.
2024-08-08 10:46:43 -07:00
Jitang Lei
7b61eba471 server/download.go: Fix a typo in log
Signed-off-by: Jitang Lei <leijitang@outlook.com>
2024-08-08 20:28:01 +08:00
Jesse Gross
7edaf6e7e8 manifest: Store layers inside manifests consistently as values.
Commit 1829fb61 ("manifest: Fix crash on startup when trying to clean up
unused files (#5840)") changed the config layer stored in manifests
from a pointer to a value. This was done in order to avoid potential
nil pointer dereferences after it is deserialized from JSON in the
event that the field is missing.

This changes the Layers slice to also be stored by value. This enables
consistency in handling across the two objects.
2024-08-07 17:03:06 -07:00
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