Lei Hao

Why the timestamp of messages based on platform?

1

Submit feature requests to http://www.mattermost.org/feature-requests/. File non-security related bugs here in the following format: #### Summary I confused why the timestamp of messages based on platform? (only if the login...

RuntimeError: Placeholder storage has not been allocated on MPS device!

2

Env: ``` macOS== 13.3.1 M1Max, 64G python==3.10.10 tensorflow-macos==2.12.0 tensorflow-metal==0.8.0 ``` It can run on Apple Silicon with CPU, but when I try to set the device to `mps` instead of...

这个续写功能特别棒，感谢作者 另外想问下后续有计划支持别的模型吗？ 比如 Baichuan-13B-Chat https://github.com/baichuan-inc/Baichuan-13B https://huggingface.co/baichuan-inc/Baichuan-13B-Chat

Support Apple Neural Engine (ANE) Transformers

1

I noticed Apple supports ANE Transformers. According to their own words: >M1 or newer chip to achieve up to **10 times faster and 14 times lower peak memory** Does that...

Added "baseten/alpaca-30b" from Hugging Face as the new Alpaca 30B model.

When Watching courses on the web, it usually can speed up at least to 2x I read the Jellyfin-expo code found the video player was implemented by using ``. In...

feat: Add Context Length Slider for Ollama Models

1

Add a new slider component to control the context length (num_ctx) parameter for Ollama models. This allows users to adjust the context window size between 8K and 128K tokens. Changes:...