ollama

pool/ollama

SHA256

Fork 2

Commit Graph

Author	SHA256	Message	Date
Loren Burkholder	cf9cf2a4df	Accepting request 1173521 from home:VaiTon:branches:science:machinelearning - Update to version 0.1.37: * Fixed issue where models with uppercase characters in the name would not show with ollama list * Fixed usage string for ollama create * Fix finish_reason being "" instead of null in the Open-AI compatible chat API. - Use obs_scm service instead of the deprecated tar_scm - Use zstd for vendor tarball compression OBS-URL: https://build.opensuse.org/request/show/1173521 OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=13	2024-05-13 03:27:47 +00:00
Guillaume GARDET	5a3ae9ab21	Accepting request 1150495 from home:LorenDB I've created a package for Ollama (https://ollama.com) so that users don't have to use an install script. I will point out that this does not have CUDA support or ROCm enabled; we won't be able to package CUDA for obvious reasons, and ROCm is currently not packaged in Factory. However, for basic CPU-enabled use, this is better than curling a random script from the interwebs :) OBS-URL: https://build.opensuse.org/request/show/1150495 OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=1	2024-02-26 09:11:49 +00:00

Author

SHA256

Message

Date

Loren Burkholder

cf9cf2a4df

Accepting request 1173521 from home:VaiTon:branches:science:machinelearning

- Update to version 0.1.37:
  * Fixed issue where models with uppercase characters in the name
    would not show with ollama list
  * Fixed usage string for ollama create
  * Fix finish_reason being "" instead of null in the Open-AI
    compatible chat API.

- Use obs_scm service instead of the deprecated tar_scm
- Use zstd for vendor tarball compression

OBS-URL: https://build.opensuse.org/request/show/1173521
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=13

2024-05-13 03:27:47 +00:00

Guillaume GARDET

5a3ae9ab21

Accepting request 1150495 from home:LorenDB

I've created a package for Ollama (https://ollama.com) so that users don't have to use an install script. I will point out that this does not have CUDA support or ROCm enabled; we won't be able to package CUDA for obvious reasons, and ROCm is currently not packaged in Factory. However, for basic CPU-enabled use, this is better than curling a random script from the interwebs :)

OBS-URL: https://build.opensuse.org/request/show/1150495
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/ollama?expand=0&rev=1

2024-02-26 09:11:49 +00:00

2 Commits