-
### 🚀 Feature
Unless I'm mistaken, stable-baselines3 only supports Box, Discrete, MultiDiscrete, MultiBinary and Dict spaces from gymnasium.
It seems like a new _fundamental space_ has been introd…
-
Hi Jason,
I followed the steps
Step 1 - Supervised Fine-tuning, generate "/checkpoints/supervised_llama/" including folders:
```
checkpoint-2000
checkpoint-3000
checkpoint-4000
final_checkp…
-
Hi there,
Thanks for the scripts and posts! I am interested in fine-tuning Mixtral 8x7b on sagemaker. The task I have requires around 8k token length.
I have tried running training following th…
-
### Problem Description
Llama3 8B FP8 OOMs at the same batch size as BF16. I need to decrease the batch size to `2` for it to not OOM. At batch size 2, TE FP8 is **21% slower** than torch compile B…
-
Hello, I would like to ask can the full training of fingpt be done on colab with A100? How long will it take.
-
**Describe the bug**
I've really been loving using simple-parsing in my projects. It looks like you are trying to maintain compatibility with hugging faces dataclass #172. One use case I've been tryi…
-
This is an amazing work. I have been working on something that would require me to evaluate the generated outputs of models like Mistral, using a prompt like:
`"Fill the [MASK] token in the sentence.…
-
We need more compute & storage than is individually available to us via local GPUs to train the MVM outlined on our Roadmap:
To engage with any potential compute & data storage providers who may be i…
-
### Problem
We want to add support for this new model that unlike the previous ones also supports vision. The readme for the model is described below:
---
language:
- en
- de
- fr
- it
- pt…
-
### Is your feature request related to a problem? Please describe.
I saw that 4-turbo is currently the default model, the issue that it's outdated and expensive, which may lead to a negative first …