-
Same here. I was pretraining LlaMA-3.1-7B-Instruct done, and then continue to finetuning w/ QLoRA normally. After 2 epochs, I switched to use Unsloth to continue the finetuning with longer context (80…
-
### Is your feature request related to a problem?
There are a bunch of different optimizers for neural networks that can have better or worse performance dependent on the data and the specific neural…
-
### Description
Scikit offers a gridsearch, where a large number of candidates (parameter configurations) is first trained on a very small batch of the training data. With each step the most promisin…
-
## Why do we need better support?
Latency is difficult to deal with, as such issues heavily depend on environments and contexts. For LTR, this is even more complex, as needs of data scientists (preci…
-
### Description
Importing models isn't the most obvious to new users. If you look at the documentation there isn't anything to indicate what the module name is and if you look in the code
```
@decl…
-
The `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.
Traceback (most recent call last):
File "/hpc2hdd/home/yhuang489/junhao/Emu3/e…
-
< Placeholder >
timeline: April 2023 - April 2027.
[Key historical 2016 issue of thesis topic](https://github.com/Tribler/tribler/issues/2250)
ToDo: 6 weeks hands-on Python onboarding project. …
-
**Is your feature request related to a problem? Please describe.**
When generating sweeps over multiple hyperparameters, I often want to group by multiple params in the charts in the app. For example…
-
### Description of the project, you want to add.
Using the dataset, ML model have been trained to detect whether a person is suffering from heart disease or not.
### Mention if this feature is for a…
-
- [ ] [Google - Gemini Long Context | Kaggle](https://www.kaggle.com/competitions/gemini-long-context)
# Google - Gemini Long Context | Kaggle
## Snippet
```
GOOGLE · ANALYTICS COMPETITION · A MONT…