-
Hi,
After succefully running SortPooling, I am experimenting with my own data set while keepenig the architecture
and have a couple of questions:
- TrajectoryData gets the size but internally produ…
tinca updated
1 month ago
-
RuntimeError: CUDA error: too many resources requested for launch
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
V100 lora 微调 qwenvl2-2b-instruct 出现上述错误
-
Hi,
I used this GCN for predicting the nodes score. The mse is loss not reducing much. It reduced from 0.2 to 0.1963. I think it is still possible to reduce, I tried adding another conv layer, but …
-
Hello, it's a great project!
I tried to use the `EMLP` with dm-haiku, and I write two version of codes in different ways. The first is directly using the `emlp.nn.haiku`, and the second is using the …
-
Hi,
I am trying to run the model on Sagemaker, but I am getting the following warning:
"Some weights of the model checkpoint at declare-lab/flacuna-13b-v1.0 were not used when initializing Llama…
-
### Background and motivation
Hi, thanks for your work.
But when I'm tring to migrate my PyTorch code to Oneflow code, I find that there are only few APIs in oneflow.distributions. So this part is …
-
Hi I wonder model weight is convertible between HF model weight and Open_clip model weight.
HF model weight : https://huggingface.co/wkcn/TinyCLIP-ViT-40M-32-Text-19M-LAION400M
Open clip model : htt…
-
### Describe the bug
When I tried to load the safetensors file into models/checkpoint, I encountered the following error and could not load it. These safetensors files were used in the stable-diffusi…
-
### Question
Hi, I have tried https://llava.hliu.cc/ and `llava.eval.run_llava` on the same image and query, but the generated captions are different, any ideas? Thanks
Since the model used in htt…
viyjy updated
11 months ago
-
## Description:
This issue proposes an enhancement to the Kolmogorov-Arnold Networks (KAN) architecture that involves the development of an automated method for converting trained models into symboli…