Gabrielle Ong
Gabrielle Ong
### # - [X] I have searched the existing issues ### Current behavior Dangling cortex and Node processes remain, even after closing Jan App / stopping cortex on command line....
**Describe the bug** `cortex run mistral:tensorrt-llm` shows loads model, but running chat returns 500 error **To Reproduce** 1. cortex run mistral:tensorrt-llm 2. cortex run mistral:tensorrt-llm --chat **Expected behavior** chat window...
Improvements to #1072  ### Edge cases - [ ] Local folder structures for cuda toolkit if user have both `llamacpp` and `tensorrt-llm` - [ ] Compatibility with user's GPU...
## Task list - [ ] Delete old .gguf and metadata.yaml files from main branch - [ ] Update default branches in metadata.yml for some models https://github.com/janhq/cortex.cpp/issues/1418#issuecomment-2392716451 ## Ongoing discussion:...
### Cortex version cortex-beta v1.0.0-rc1 ### Describe the Bug When reading from metadata.yml, default branch was not detected due to `34B` vs `34b`   Existing branches may have inconsistent...
## Problem - user downloads hugging face model using author/model_id, eg ``` cortex pull bartowski/Meta-Llama-3.1-8B-Instruct-GGUF ``` - In `cortex models list`, the alias is unexpectedly different. ``` cortex run meta-llama-3.1-8b-instruct-q2_k...
v141 
Discussion: https://github.com/janhq/cortex.cpp/discussions/1386
### Cortex version v1.0.0-141 ### Describe the Bug Issue faced when running an already downloaded huggingface model author/model_id ``` > cortex-nightly run bartowski/Meta-Llama-3.1-8B-Instruct-GGUF ... Selected: Meta-Llama-3.1-8B-Instruct-Q2_K.gguf Model already downloaded: bartowski:Meta-Llama-3.1-8B-Instruct-GGUF:Meta-Llama-3.1-8B-Instruct-Q2_K.gguf...
Ice boxed, as Cortex currently does not support vision models (no template for model.yml)