-
We know that flash attention supports `cu_seqlens`, which can remove padding for variable-length input in a batch and only store regular tokens. This can be useful for optimizing the computational eff…
-
I'm having an issue trying to get mamba running on 3xP40. The model will load into vram but then crashes with "RuntimeError: CUDA error: no kernel image is available for execution on the device" I …
-
**Please check the [Github](https://github.com/zezhishao/MTS_Daily_ArXiv) page for a better reading experience and more papers.**
## Time Series
| **Title** | **Date** | **Comment** |
| --- | --- | -…
-
```shell
09/10 [07:43:21] INFO | >> [*] Loading from local path `/code/Basemodel/ML-Mamba` …
-
Hi @hotfinda ,
Could you please share the actual implementation of the paper that can re-produce the results you reported in the paper?
Basically, the current code is not running.
(1) For the…
-
Hello, I am trying to implement a mamba based model, whenever I try to increase d_model above 100 I get this error message. I am using torch.cuda.amp for mixed precision training.
here is the mod…
-
Amazing work, and I'm inspired by the connections to dynamical systems.
Would you mind showing us a minimal example of training or finetuning this?
-
# What We Know About The Voynich Manuscript
-
Hi @theodorblackbird
Currently, the model sounds good but I think if you scale the model it will get better with picking prosody and timber from prompt and sounds much more natural.
One suggest I c…
-
**LocalAI version:**
quay.io/go-skynet/local-ai:v1.18.0-ffmpeg
localai/localai:v2.17.1-ffmpeg
**Environment, CPU architecture, OS, and Version:**
rtx4060/ryzen5700/32G
**Describe the …