nguyenhoangthuan99

Dear @fbens47, It’s been a long time and I don’t remember the details. But as I remember, I converted the model to onnx and use ONNx parser on python code,...

This feature is already supported in llamacpp and Jan also supported it. But first of all, we need to make sure that the multi-part gguf file is splited properly. Examples:...

Logic for generating short aliases for models in the nightly version: 1. Start with the unique model ID, e.g., `huggingface.co:bartowski:Meta-Llama-3.1-8B-Instruct-GGUF:Meta-Llama-3.1-8B-Instruct-Q2_K` 2. Check if the lowercase version of the last part...

# cortex.db Models Table Structure and User Experience Improvements ## 1. Models Table Structure The `Models` table should contain 3 fields: - Model Alias (can be overloaded with multiple versions)...

# 1. Models Table Structure I think it clear now, The `Models` table in cortex.db still remains the same as before | model table | Description | |--------|--------| | `model`...

With this new change, I believe `alias` functions more as a model group than a short name, making it easier for users to manage models. However, without aliases, we could...

Update: - under development in this branch https://github.com/janhq/cortex/tree/feat-background-process-server/engine/test - when build add an option to decide build test or not: `cmake .. -DCMAKE_BUILD_TEST=ON` [source code](https://github.com/janhq/cortex/blob/feat-background-process-server/engine/CMakeLists.txt#L84) here. Default is `OFF` ->...

Stop words of a model can be a list so I think we can make it like this  From technical aspect, I think there are 2 cases we can...

The `import` command is supported with this PR #1248

# Model Hub API Implementation ## Overview We are implementing a Model Hub API to enable organizations and users to add external model hubs (HuggingFace, NGC Cloud, etc.) to their...