Overview
Request 1174423 revoked
- Update to version 0.1.38:
* fix the cpu estimatedTotal memory + get the expiry time for loading models (#4461)
* Sanitize the env var debug log
* fix typo in modelfile generation (#4439)
* fix keepalive for non-interactive mode (#4438)
* re-add system context (#4435)
* Fixed the API endpoint /api/tags when the model list is empty. (#4424)
* Remove VRAM convergence check for windows
* don't abort when an invalid model name is used in /save (#4416)
* update the FAQ to be more clear about windows env variables (#4415)
* Ollama `ps` command for showing currently loaded models (#4327)
* removed inconsistencies
* typo
* count memory up to NumGPU
* removed inconsistent punctuation
* Correct typos. (#4387)
* Update `LlamaScript` to point to new link.
* Revert "use post token"
* use post token
Request History
kskarthik created request
- Update to version 0.1.38:
* fix the cpu estimatedTotal memory + get the expiry time for loading models (#4461)
* Sanitize the env var debug log
* fix typo in modelfile generation (#4439)
* fix keepalive for non-interactive mode (#4438)
* re-add system context (#4435)
* Fixed the API endpoint /api/tags when the model list is empty. (#4424)
* Remove VRAM convergence check for windows
* don't abort when an invalid model name is used in /save (#4416)
* update the FAQ to be more clear about windows env variables (#4415)
* Ollama `ps` command for showing currently loaded models (#4327)
* removed inconsistencies
* typo
* count memory up to NumGPU
* removed inconsistent punctuation
* Correct typos. (#4387)
* Update `LlamaScript` to point to new link.
* Revert "use post token"
* use post token
LorenDB declined request
Thank you, but somebody else already submitted the 0.1.38 update :)
kskarthik revoked request
@LorenDB ok