Get up and running with Llama 2, Mistral, Gemma, and other large language models.
https://ollama.com
Get up and running with Llama 2, Mistral, Gemma, and other large language models.
You can find a list of models available for use at https://ollama.com/library.
- Developed at science:machinelearning
- Sources inherited from project openSUSE:Factory
-
3
derived packages
- Download package
-
Checkout Package
osc -A https://api.opensuse.org checkout openSUSE:Backports:SLE-15-SP4:FactoryCandidates/ollama && cd $_ - Create Badge
Refresh
Refresh
Source Files
| Filename | Size | Changed |
|---|---|---|
| _service | 0000000805 805 Bytes | |
| _servicedata | 0000000234 234 Bytes | |
| enable-lto.patch | 0000001472 1.44 KB | |
| ollama-0.1.48.obscpio | 0160434702 153 MB | |
| ollama-user.conf | 0000000090 90 Bytes | |
| ollama.changes | 0000019872 19.4 KB | |
| ollama.obsinfo | 0000000096 96 Bytes | |
| ollama.service | 0000000193 193 Bytes | |
| ollama.spec | 0000002682 2.62 KB | |
| vendor.tar.zstd | 0005307324 5.06 MB |
Revision 11 (latest revision is 24)
Ana Guerrero (anag+factory)
accepted
request 1186033
from
Eyad Issa (VaiTon)
(revision 11)
- Update to version 0.1.48:
* Fixed issue where Gemma 2 would continuously output when
reaching context limits
* Fixed out of memory and core dump errors when running Gemma 2
* /show info will now show additional model information in
ollama run
* Fixed issue where ollama show would result in an error on
certain vision models
- Update to version 0.1.48:
* Added support for Google Gemma 2 models (9B and 27B)
* Fixed issues with ollama create when importing from Safetensors
- Update to version 0.1.46:
* Docs (#5149)
* fix: quantization with template
* Fix use_mmap parsing for modelfiles
* Refine mmap default logic on linux
* Bump latest fedora cuda repo to 39
Comments 0