-
## Environment
- llm-foundry: latest
## To reproduce
Steps to reproduce the behavior:
1. train a `hf_t5` model
2. download the composer checkpoint
3. try to convert it back to huggingface…
-
-
There seems to be an issue with the included texar module.
I installed it as described in the README via `pip install -e .` but it cannot be imported:
```
>>> import texar
Traceback (most rece…
swidi updated
3 years ago
-
This is a illustration of the seq2seq model with attention for DLpredictor.
![seq2seq_plus_attention](https://user-images.githubusercontent.com/60371672/154518241-1d05ebe3-592e-416f-a03a-5ef272739f98…
-
C:\ProgramData\Anaconda3\envs\torch\python.exe E:/hyx/seq2seq-master/seq2seq.py train
C:\ProgramData\Anaconda3\envs\torch\lib\site-packages\torch\nn\modules\rnn.py:54: UserWarning: dropout option add…
-
self.outputs, self.losses = tf.nn.seq2seq.model_with_buckets(
self.encoder_inputs,
self.decoder_inputs,
…
-
I ran this command
"python src/launcher.py --phase=test --visualize --data-path=evaluation_data/svt/test.txt --data-base-dir=evaluation_data/svt --log-path=log.txt --load-model --model-dir=model --o…
-
Em đang thử train model seq2seq với dataset. Sau khi train xong và sử dụng thì thấy có vẻ một số ảnh chưa được train.
Sau khi lọc ra thì thấy những ảnh bên dưới không được train.
Khi thử train chỉ n…
-
### Problem Description
When I use seq2seq model,such as TCN or LSTM or Transformer,they are have two inputs,one is x,another is y.And x's shape is different with y's shape,for example x's shape is (…
-
I used this code.
import tensorflow as tf
import numpy as np
# preprocessed data
from datasets.twitter import data
import data_utils
# load data from pickle and npy files
metadata, idx_q, i…