Rafael dos Santos Silva

> Since SentenceTransformers recommend all-mpnet-base-v2 I imagine lots of projects, like us, are using that model. Worth adding that `all-mpnet-base-v2` is the top 1 model by downloads in the hub...

@OlivierDehaene sorry for the direct ping, but could you share a spit ball guess on how hard would be to add support for `all-mpnet-base-v2` ? Wondering if this is something...

> You wont be able to use flash attention though so it will be slower than other models. Thanks for mentioning that. In that case it may be worth to...

@johnnyshields do you plan to keep updating your current dart-sass branch? I'd convert it to a full fork, with open issues, and merge it to your main branch and start...

> To alleviate the above, I have implemented the SSE, AVX and AVX512F versions of the vector operations, and added a CPU dispatching mechanism (during extension load time) to pick...

@jkatz is this something you still want to pursue? This would be great to simplify my use case at @discourse where we automated the index creation, but setting this parameter...

> @xfalcox Yes, I'd be interested in pursuing it -- the RFC is out there to collect use cases before adding to the code 😄 I don't think a PR...

> But i'm getting a Failed to buffer the request body: length limit exceeded error if my request gets bigger than 2MB. Now you can pass `--payload-limit ` to handle...

> The problem is there's no way to use the sparse or colbert features of this model I too would be interested on the `/embed_sparse` endpoint working with the `bge-m3`...

> Do we know which of the tweaks breaks Ruby? We need to report this to https://bugs.ruby-lang.org/ - can you make it so? While working on a minimal repro to...