Downloads · 30 days
0
CohleM/best_model_sft_4epoch
best_model_sft_4epoch is a machine learning model from CohleM. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
LilLM 39M parameter model fine-tuned on SFT dataset.
Downloads · 30 days
0
Access
Public
Updated Feb 25, 2025
Repo size
475 MB
Likes
0
Public
Click a slice to open those files.
.pt475 MB · 100%
From the Hugging Face model README
LilLM 39M parameter model fine-tuned on SFT dataset.
The dataset only includes examples with sequence length < 512 (according to our own tokenizer)
Find the SFT dataset here: https://huggingface.co/datasets/CohleM/lillm-sft-dataset-512-including-hard-coded-mixture Find the data-preparation file here: https://colab.research.google.com/drive/1QkIpkhaZVNvZwBoD69N5O-md5FjRSW_W