-
Hi all,
I want to use EBM as a GAM to replace the fully connected layer at the end of a large CNN/Transformer to get interpretable output. However, I need to train the EBM like a deep learning model,…
-
I ran these commands in Google Colab with GPU
```
!wget http://boston.lti.cs.cmu.edu/luyug/coil/msmarco-psg/psg-train.tar.gz
!tar xfz psg-train.tar.gz
!git clone https://github.com/luyug/COIL
!…
-
### System Info
linux
### Who can help?
@pacman100 @younesbelkada @BenjaminBossan
When I used prefix tuning to fine-tune codebert for sequence classification, it showed the following erro…
-
Hi,
While I am trying the training code with m4c_captioner model, I am getting the following error,
/home/root1/anaconda3/envs/mmf/lib/python3.7/site-packages/omegaconf/grammar_visitor.py:257: U…
-
Thanks for the great work.
I try to train the ldm model on ImageNet with 8 V100, but get a bad result.I found that loss was normal at first, but soon collapsed:
![image](https://user-images.githu…
-
Similar to the issue I posted here: https://github.com/openai/gpt-2/issues/148
-- Is it possible to use the intermediate layer outputs and generate text ignoring the layers on top?Basically, I want t…
-
AttributeError: 'BaichuanTokenizer' object has no attribute 'sp_model'
-
Hi,
When running `finetune-mbart-on-transaltion_embed+xattn.sh` I get the error `TypeError: forward() missing 1 required positional argument: 'prev_output_tokens' in the beginning of epoch 1.` When…
-
环境
---
```shell
(base) [root@localhost ~]# nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Mon_Apr__3_17:16:06_PDT_2023
Cuda compilation tool…
-
I've been trying to make the combination `deepspeed + qlora + falcon` work but due to unknown reasons I've stuck in an error maze.
## Setup
- Docker image: `winglian/axolotl-runpod:main-py3.9-cu…