-
loss降到0.11左右就降不下去了,推理结果有点欠拟合,应该如何解决?试图调过学习率但没有太大效果。
-
Hello I am running a 2x 4090 PC, Windows, with exllama on 7b llama-2.
I am only getting ~70-75t/s during inference (using just 1x 4090), but based on the charts, I should be getting 140+t/s.
Wha…
-
Everything's fine up to the actual training point, but the cmd throws some error and I don't get my pth and index files.
```
write filelist done
use gpus: 0
runtime\python.exe train_nsf_sim_cac…
-
{
"id": "000000245946",
"image": "000000245946.jpg",
"conversations": [
{
"from": "human",
"value": "\nWhat considerations…
-
Used the following lines for env creation
****
conda create --name unsloth_env python=3.10
conda activate unsloth_env
conda install pytorch-cuda= pytorch cudatoolkit xformers -c pytorch -c nvi…
-
### 🚀 The feature, motivation and pitch
For large tensors, neighborhood algorithms are limited by large memory requirements, for example the squared-distance matrix of KNN.
Speaking from my fiel…
-
### Describe the bug
[2024-08-08T07:17:44,731][WARN ][a.d.h.t.HuggingFaceTokenizer] [opensearch-ml-node] maxLength is not explicitly specified, use modelMaxLength: 512
[2024-08-08T07:17:44,737][ER…
-
Hi Tushar,
I urgently need sm help in implementing drone detection and tracking. Can you help me implement/ resolve issues implementing your drone detection project ??.....please share your contac…
-
Hi, thanks for such a great repo! 🤗
I wanted to train `YOLOr` on my own custom data. This is the command I am using, in `Colab`:-
```py
#Set Epochs
EPOCHS = 30
BATCH_SIZE = 32
!python /content/…
-
Hi!
This is a really great tool and it's been fun using it.
I am trying to train the model 'bert-base-multilingual-uncased' using a tokenized dataset in the correct format. But every time I run the…
ghost updated
2 years ago