neurallambda

I was just playing around, and didn't necessarily settle on `TensorProduct (R n) w = [w]`. I feel a bit out of my league even commenting on this, but: *...

No worries! My impression of Agent, and I could be wrong, wat that it recreates portions of proc syntax. I find I still struggle to think in terms of point-free...

Ya, `Pair` and the typeclass were 2 different approaches to the same problem, and could work, but, I'm not totally convinced it's the right design yet. It may be, just,...

I'm interested! @leftaroundabout, I've enjoyed perusing your libraries, and the other "category" and linalg libraries in this space, and haven't been able to find a connection between all these concepts....

Awesome! Thanks for the leads, I think that's enough to get started, and I'll try and find some time this weekend.

I've started adding the HMatrix backend here: https://github.com/leftaroundabout/linearmap-family/pull/6 I'll think some more about the `TensorSpace` issues you've mentioned, as, I'm sure you will too. I have a little experience using...

Thanks for the contribution! Would you mind fixing the links though, they're too verbose? Right now many links in this doc are collapsed like this: ``` [`[1]`](https://reasoning-tokens.ghost.io/reasoning-tokens/) ``` But it...

I have this same missing symbol using: ``` torch==2.3.1 flash-attn==2.5.9.post1 Cuda 12.2 ``` **edit:** This resolved it for me finally ```sh pip uninstall flash-attn git clone https://github.com/Dao-AILab/flash-attention pip install -e...

I'm facing the same issue: https://github.com/abetlen/llama-cpp-python/issues/1123#issuecomment-2153405068 I've also tried reinstalling it: ```sh CMAKE_ARGS="-DLLAMA_CUDA=on" pip install --force-reinstall --no-cache-dir llama-cpp-python ``` And also tried setting `n_gpu_layers` and `tensor_split`. None of the above...

:+1: Batch inference would greatly unlock **synthetic data**. **edit:** in the meantime, [`outlines`](https://github.com/outlines-dev/outlines) offers constrained gen and batch inference.