Pierrick Hymbert

Hello everyone, The workflow is deployed since one week, and some concerns have been identified: - PR Comment can be distratful or inappropriate, for example, one marks "This comment was...

@ggerganov the node seems to be down. Maybe we should configure the runner as a service ? Also, note that I did not forget to revert xk6-sse, I will do...

Dbrx is a gated model, so I believe you have to pass a read token. There is an issue open on llama.cpp to support this.

sliding window for phi3 implemented and defaulted in: - #8627 - #8931 Cannot reproduce : llama-cli --hf-repo microsoft/Phi-3-mini-4k-instruct-gguf ``` llama-cli --hf-repo microsoft/Phi-3-mini-4k-instruct-gguf --hf-file Phi-3-mini-4k-instruct-q4.gguf -p "At eight o clock Kutuzov...

Have you seen: [gguf-dump](https://github.com/ggerganov/llama.cpp/blob/master/gguf-py/scripts/gguf-dump.py) for printing metadata ? Or do you want something dynamic during the forward ?

For the archive: [Bitbucket data-center-end-of-life](https://www.atlassian.com/licensing/data-center-end-of-life) But AFAICT no one knows what will be agentic coding in 3 years. I am also fine to simply close this feature request if it...

How I can help to get feedback on this feature ? I can understand it's enterprise oriented, but is not the open-source spirit of openhands ? Without this I can't...

Kindly request to review this

Great @OmegAshEnr01n , few notes: - I think we need 2 subcharts, one for embeddings, one for generation/completions - probably need to update the schema in my branch as now...

Hi @OmegAshEnr01n, are you still working on this issue ?