Jeffrey Morgan
b9f91a0b36
Update import instructions to use convert and quantize tooling from llama.cpp submodule ( #2247 )
2024-02-05 00:50:44 -05:00
Erik S
b538dc3858
Add llm-ollama plugin for Datasette's LLM CLI to README ( #2340 )
...
Co-authored-by: Erik Sp <git@aschwa.com>
2024-02-03 15:40:50 -08:00
Jeffrey Morgan
f0e9496c85
Update api.md
2024-02-02 12:17:24 -08:00
Jeffrey Morgan
09a6f76f4c
fix error on ollama run with a non-existent model
2024-02-01 23:11:52 -08:00
Jeffrey Morgan
e135167484
Add multimodel support to ollama run in noninteractive mopde ( #2317 )
2024-02-01 21:33:06 -08:00
Jeffrey Morgan
38296ab352
clear previous images when submitting an image to ollama run ( #2316 )
2024-02-01 21:30:26 -08:00
Daniel Hiltgen
f43dea68d1
Merge pull request #2318 from dhiltgen/more_clean
...
Harden generate patching model
2024-02-01 20:41:29 -08:00
Daniel Hiltgen
e1f50377f4
Harden generate patching model
...
Only apply patches if we have any, and make sure to cleanup
every file we patched at the end to leave the tree clean
2024-02-01 19:34:36 -08:00
Jeffrey Morgan
7913104527
Improvements to ollama run for multimodal models ( #2300 )
2024-02-01 17:09:51 -08:00
Michael Yang
bfbf2f7cf7
Merge pull request #2296 from ollama/mxyng/img-tags
...
append image tags to user content
2024-02-01 13:16:59 -08:00
Michael Yang
fe3cbd014f
Merge pull request #2298 from ollama/mxyng/debug-prompt
...
structured debug prompt
2024-02-01 13:16:49 -08:00
Michael Yang
3d6f48507a
structured debug prompt
2024-02-01 11:56:28 -08:00
Michael Yang
f3761405c8
use image id
2024-02-01 11:52:42 -08:00
Michael Yang
e49dc9f3d8
fix tests
2024-02-01 11:48:11 -08:00
Michael Yang
d125510b4b
remove image tags
2024-02-01 11:32:51 -08:00
Russell Canfield
1ca386aa9e
Feature - Add Wingman Extension ( #2313 )
2024-02-01 11:16:24 -08:00
Michael Yang
fb56988014
account for image projection in token count
2024-02-01 09:50:48 -08:00
Michael Yang
d046bee790
use llm.ImageData for chat
2024-01-31 19:18:25 -08:00
Jeffrey Morgan
f11bf0740b
use llm.ImageData
2024-01-31 19:13:48 -08:00
Michael Yang
8450bf66e6
trim images
2024-01-31 19:13:47 -08:00
Michael Yang
b4e11be8ef
append image tags to user content
2024-01-31 19:13:10 -08:00
Bruce MacDonald
a896079705
preserve last system message from modelfile ( #2289 )
2024-01-31 21:45:01 -05:00
Michael Yang
583950c828
Merge pull request #2294 from ollama/mxyng/slog-source
...
update slog handler options
2024-01-31 15:29:11 -08:00
Michael Yang
8ac08a0eec
update slog handler options
...
- consistent format by using text handler for debug and non-debug
- truncate source file to just the file name
2024-01-31 15:15:00 -08:00
Michael Yang
60f47be64c
Merge pull request #2284 from ollama/mxyng/parse-raw
...
remove unnecessary parse raw
2024-01-31 09:40:48 -08:00
Daniel Hiltgen
6e56077ada
Merge pull request #2263 from dhiltgen/bump_llamacpp
...
Bump llama.cpp to b1999
2024-01-31 08:39:41 -08:00
Hoang Nguyen
98ae9467bb
Added MindMac to Community Integrations -> Web & Desktop section ( #1957 )
2024-01-31 07:48:37 -08:00
Richard Macarthy
b7a24af083
Add twinny vscode extension to Extensions and Plugins ( #1950 )
2024-01-31 06:25:06 -08:00
Michael Yang
c8b1f2369e
remove unnecessary parse raw
2024-01-30 17:00:53 -08:00
Daniel Hiltgen
72b12c3be7
Bump llama.cpp to b1999
...
This requires an upstream change to support graceful termination,
carried as a patch.
2024-01-30 16:52:12 -08:00
Bruce MacDonald
0632dff3f8
trim chat prompt based on llm context size ( #1963 )
2024-01-30 15:59:29 -05:00
Maximilian Weber
509e2dec8a
Update README.md ( #2252 )
...
Added - [Ollama for R - rollama](https://github.com/JBGruber/rollama ) in Libraries in README.md
2024-01-30 11:56:51 -08:00
Daniel Hiltgen
78a48de804
Merge pull request #2256 from dhiltgen/container_logs
...
Add container hints for troubleshooting
2024-01-30 08:12:48 -08:00
Daniel Hiltgen
e7dbb00331
Add container hints for troubleshooting
...
Some users are new to containers and unsure where the server logs go
2024-01-29 08:53:41 -08:00
Marc Raiser
c3f9538636
remove default.nix
2024-01-29 00:05:07 -05:00
Jeffrey Morgan
2e06ed01d5
remove unknown CPPFLAGS option
2024-01-28 17:51:23 -08:00
Daniel Hiltgen
4072b5879b
Merge pull request #2246 from dhiltgen/reject_cuda_without_avx
...
Don't disable GPUs on arm without AVX
2024-01-28 16:26:55 -08:00
Daniel Hiltgen
15562e887d
Don't disable GPUs on arm without AVX
...
AVX is an x86 feature, so ARM should be excluded from
the check.
2024-01-28 15:22:38 -08:00
Jeffrey Morgan
f2245c7c77
print prompt with OLLAMA_DEBUG=1 ( #2245 )
2024-01-28 15:22:35 -08:00
Jeffrey Morgan
e4b9b72f2a
Do not repeat system prompt for chat templating ( #2241 )
2024-01-28 14:15:56 -08:00
Daniel Hiltgen
311f8e0c3f
Merge pull request #2243 from dhiltgen/harden_zero_gpus
...
Harden for zero detected GPUs
2024-01-28 13:30:44 -08:00
Daniel Hiltgen
f07f8b7a9e
Harden for zero detected GPUs
...
At least with the ROCm libraries, its possible to have the library
present with zero GPUs. This fix avoids a divide by zero bug in llm.go
when we try to calculate GPU memory with zero GPUs.
2024-01-28 13:13:10 -08:00
mraiser
4c4c730a0a
Merge branch 'ollama:main' into main
2024-01-27 21:56:11 -05:00
Daniel Hiltgen
e02ecfb6c8
Merge pull request #2116 from dhiltgen/cc_50_80
...
Add support for CUDA 5.0 cards
2024-01-27 10:28:38 -08:00
Daniel Hiltgen
c8059b4dcf
Merge pull request #2224 from jaglinux/fix_rocm_get_version_message
...
ROCm: Correct the response string in rocm_get_version function
2024-01-27 07:29:32 -08:00
Jagadish Krishnamoorthy
59d87127f5
Update gpu_info_rocm.c
2024-01-26 22:08:27 -08:00
Patrick Devine
b5cf31b460
add keep_alive to generate/chat/embedding api endpoints ( #2146 )
2024-01-26 14:28:02 -08:00
Daniel Hiltgen
cc4915e262
Merge pull request #2214 from dhiltgen/reject_cuda_without_avx
...
Detect lack of AVX and fallback to CPU mode
2024-01-26 12:06:44 -08:00
Daniel Hiltgen
667a2ba18a
Detect lack of AVX and fallback to CPU mode
...
We build the GPU libraries with AVX enabled to ensure that if not all
layers fit on the GPU we get better performance in a mixed mode.
If the user is using a virtualization/emulation system that lacks AVX
this used to result in an illegal instruction error and crash before this
fix. Now we will report a warning in the server log, and just use
CPU mode to ensure we don't crash.
2024-01-26 11:36:03 -08:00
Michael Yang
e054ebe059
Merge pull request #2212 from ollama/mxyng/fix-build
...
fix build
2024-01-26 11:19:08 -08:00
