Jeffrey Morgan
9e4a316405
update submodule commit
2023-11-26 14:52:00 -05:00
Jeffrey Morgan
9fb5e8399c
Fix issues with inputting and formatting multi line strings in ollama run
...
Co-authored-by: Wen Sun <iwendellsun@gmail.com>
2023-11-26 12:54:29 -05:00
Jing Zhang
82b9b329ff
windows CUDA support ( #1262 )
...
* Support cuda build in Windows
* Enable dynamic NumGPU allocation for Windows
2023-11-24 17:16:36 -05:00
Jongwook Choi
12e8c12d2b
Disable CUDA peer access as a workaround for multi-gpu inference bug ( #1261 )
...
When CUDA peer access is enabled, multi-gpu inference will produce
garbage output. This is a known bug of llama.cpp (or nvidia). Until the
upstream bug is fixed, we can disable CUDA peer access temporarily
to ensure correct output.
See #961 .
2023-11-24 14:05:57 -05:00
Jeffrey Morgan
d77dde126b
consistent cpu instructions on macos and linux
2023-11-22 16:26:46 -05:00
Michael Yang
c7e70cd3bb
Merge pull request #1245 from jmorganca/mxyng/gguf-int
...
fix: gguf int type
2023-11-22 11:42:56 -08:00
Michael Yang
199941cd15
fix: gguf int type
2023-11-22 11:40:30 -08:00
Long Huynh
c9474f7f61
Update README.md - Community Integrations - Obsidian BMO Chatbot plugin ( #1239 )
2023-11-22 14:32:30 -05:00
Jeffrey Morgan
927e3ba4a4
tag image with correct version when building with build_docker script
2023-11-22 14:32:17 -05:00
Bruce MacDonald
37d95157df
fix relative path on create ( #1222 )
2023-11-21 15:43:17 -05:00
Jeffrey Morgan
2eaa95b417
Update api.md
2023-11-21 15:32:05 -05:00
Kevin Cao
3cd07728f4
Make alt+backspace delete word ( #1223 )
2023-11-21 12:26:47 -08:00
Michael Yang
ecf8b793f0
Merge pull request #1224 from jmorganca/mxyng/update
...
update llama.cpp
2023-11-21 12:21:59 -08:00
Matt Williams
abf294826b
Merge pull request #1221 from jmorganca/mattw/communityinstalls
...
add installation packages category to community
2023-11-21 12:12:23 -08:00
Steve Korshakov
ae06bb426b
add Llama Coder ( #1225 )
...
* add Llama Coder
* Update README.md
2023-11-21 14:08:19 -05:00
Matt Williams
d8e0f62ebb
Merge pull request #1159 from jmorganca/mattw/functioncalling
...
Example: Function Calling in Typescript
2023-11-21 10:06:55 -08:00
Michael Yang
a00fac4ec8
update llama.cpp
2023-11-21 09:50:02 -08:00
Jeffrey Morgan
f2113c1fc7
fix potential error in progress bar calculation
2023-11-21 12:48:20 -05:00
Jeffrey Morgan
6452e2ecb8
fix cases where progress bar would not be fixed size
2023-11-21 12:07:25 -05:00
Matt Williams
9a28e263a5
Update README.md
...
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-21 07:25:32 -08:00
Matt Williams
0c066c9214
Update README.md
...
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-11-21 07:25:26 -08:00
Jeffrey Morgan
aabd71aede
fix rendering and variable width issues on progress bar
2023-11-21 10:02:37 -05:00
Matt Williams
da4d7c9f9c
add installation packages category to community
...
Moved the arch package and someone has added a pr for brew.
that needs to get updated to be a link.
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-21 06:40:59 -08:00
Matt Williams
f321b13a03
Merge pull request #1178 from tusharhero/install-instructions-archlinux
...
Add Installation instructions for Archlinux
2023-11-21 06:33:22 -08:00
Matt Williams
5ebcde1541
Merge branch 'main' into install-instructions-archlinux
2023-11-21 06:32:50 -08:00
Matt Williams
45206cb7cc
Merge pull request #1218 from danemadsen/main
...
Update Maid repo
2023-11-21 06:30:33 -08:00
Matt Williams
6e65b84f54
Merge pull request #1219 from dustinblackman/main
...
docs: Add Oatmeal to terminal integrations
2023-11-21 06:28:12 -08:00
Dustin Blackman
c00ce12e83
docs: Add Oatmeal to terminal integrations
2023-11-21 06:47:43 -05:00
tusharhero
e1cd3152c9
Move Archlinux package to Community Integrations section.
2023-11-21 16:28:50 +05:30
Dane Madsen
0bef3778c9
Update README.md
2023-11-21 21:02:13 +11:00
Dane Madsen
6ebab38b89
Merge branch 'jmorganca:main' into main
2023-11-21 20:01:13 +10:00
Dane Madsen
5d8e864d44
Update Maid repo
2023-11-21 21:00:54 +11:00
Matt Williams
5f7acd0bbd
remove 'recent'
...
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 17:03:25 -08:00
Matt Williams
44b3a1ad42
Merge branch 'mattw/functioncalling' of github.com:jmorganca/ollama into mattw/functioncalling
...
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 17:01:41 -08:00
Matt Williams
0260be4414
remove 'recently'
...
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-11-20 16:57:07 -08:00
Jeffrey Morgan
a3fcecf943
only set main_gpu if value > 0 is provided
2023-11-20 19:54:04 -05:00
Jeffrey Morgan
df07e4a097
remove redundant filename parameter ( #1213 )
2023-11-20 17:05:36 -05:00
Michael Yang
0b7ade0d4c
Merge pull request #1212 from jmorganca/mxyng/metal
...
enable metal for fp32, q5_0, q5_1
2023-11-20 13:56:39 -08:00
Michael Yang
19b7a4d715
recent llama.cpp update added kernels for fp32, q5_0, and q5_1
2023-11-20 13:44:31 -08:00
Bruce MacDonald
31ab453d37
resolve FROM path before sending modelfile ( #1211 )
2023-11-20 16:43:48 -05:00
Jeffrey Morgan
35c4b5ec16
calculate hash separately from http request
2023-11-20 15:45:11 -05:00
James Braza
f24741ff39
Documenting how to view Modelfiles ( #723 )
...
* Documented viewing Modelfiles in ollama.ai/library
* Moved Modelfile in ollama.ai down per request
2023-11-20 15:24:29 -05:00
Jeffrey Morgan
8c4022b06b
fix initial progress stats
2023-11-20 14:33:46 -05:00
Jeffrey Morgan
433702f421
hide progress stats on completion
2023-11-20 14:22:39 -05:00
Matt Williams
48896f626c
Update examples/typescript-functioncalling/extractwp.ts
...
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-20 10:12:10 -08:00
Matt Williams
c57aee6fba
Update examples/typescript-functioncalling/readme.md
...
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
2023-11-20 10:10:42 -08:00
Jeffrey Morgan
6066c70edd
restore progress messages for older endpoints
2023-11-20 11:37:17 -05:00
Jeffrey Morgan
f10ac5de19
restore stats updated every second to progress bar
2023-11-20 10:58:19 -05:00
Jeffrey Morgan
93a108214c
only show decimal points for smaller file size numbers
2023-11-20 10:58:19 -05:00
Purinda Gunasekara
be61a81758
main-gpu argument is not getting passed to llamacpp, fixed. ( #1192 )
2023-11-20 10:52:52 -05:00
