Downloads · 30 days
28
5% of all-time downloads
Llama-3.2-1B-dal-overtrained
asda488/Llama-3.2-1B-dal-overtrained
Llama-3.2-1B-dal-overtrained is a machine learning model from asda488. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
Over fine-tune of quantised LLaMa 3.2 1B on this dataset (12 epochs).
All-time downloads
616
Public
Repo size
10.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4 GB · 37%
At a glance
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Oct 1, 2024
- Updated
- Oct 2, 2024
- SHA
- 45c2da08
Base models
Model card
From the Hugging Face model README
Llama-3.2-1B-dal-overtrained
Over fine-tune of quantised LLaMa 3.2 1B on this dataset (12 epochs).
As with other overtrained models, temperature above 0.5-0.7 and high values of sampling parameters will result in the model producing garbage or the dataset source material regardless of current context.
Framework versions
- PEFT 0.13.0
- Trained with unsloth on Colab.
- Library
- peft
- Type
- llama
- Created
- Oct 1, 2024
- Updated
- Oct 2, 2024