Kostiantyn Hlushak

Thanks again for your tremendous work on this project! 1. No, it's not exactly what I meant. Let's assume that you have both source and translation for some sentence. And...

I implemented PoC for Lua version of this feature a while ago, and here is the main idea. During inference time: 1. Tokenize translation 2. Pass token_ids to beam_search 3....

Thank you for this detailed info!

But it will? )

``` environment: - PRELOAD_MODELS=["Systran/faster-whisper-medium"] ``` works for me

``` services: faster-whisper-server-cuda: image: fedirz/faster-whisper-server:latest-cuda build: dockerfile: Dockerfile.cuda context: . platforms: - linux/amd64 - linux/arm64 restart: unless-stopped ports: - 8000:8000 environment: - PRELOAD_MODELS=["Systran/faster-whisper-medium"] volumes: - hugging_face_cache:/root/.cache/huggingface develop: watch: - path:...

Just in case somebody would be wondering about how to apply solution above. Here's where I inserted it into the displaylink-debian.sh to fix the issue (wasn't obvious for me from...

I just created a PR to support this: https://github.com/dhruvyad/uttertype/pull/6 Please take a look

Just in case someone would find this issue, like I did a few weeks ago, without knowing any workaround. Currently probably one of the easiest ways import multifile gguf into...

Here's the official documentation on how agents should use their API: https://docs.github.com/en/copilot/building-copilot-extensions/building-a-copilot-agent-for-your-copilot-extension/using-copilots-llm-for-your-agent I think it's quite a strong sign that they allow such usage.