Sean Micek
Sean Micek
Why only for ollama?? How can I set this for LM studio?
Canonical code that used to run doesn't seem to anymore. `ds = xr.open_dataset(... progress(ds)` Seems distributed is just broken then? Adding client.compute(ds) in between has no effect either.
No, just that it wants 600GB memory. Do y'all have more info on memory benchmarks? The official repo mentions 60GB but not which optimizations they may be using. With a...
Any memory benchmarks are good (cuda or mps). The published numbers are only from the official hunyuan repo, and these things on arxiv are never peer reviewed anyway so like...
Hm MLX is higher maintenance to generate random tensors. It's possible MPS requires extra boilerplate too to manage memory correctly. https://github.com/ml-explore/mlx/issues/2254#event-18086129505
same here ``` from caption import caption caption(imgpth,batch_size=50) ``` It nags you about this first before proceeding to crap the bed with the error posted by OP: ``` BertLMHeadModel has...