File size: 394 Bytes
3dedadf
 
 
 
 
 
 
d30a25f
3dedadf
 
1
2
3
4
5
6
7
8
9
10
---
datasets:
- cerebras/SlimPajama-627B
base_model:
- meta-llama/Llama-3.2-1B-Instruct
---

Token frequency statistics based on [SlimPajama-627B](https://huggingface.co/datasets/cerebras/SlimPajama-627B), used for FR-Spec (https://arxiv.org/abs/2502.14856), see more at https://github.com/thunlp/FR-Spec.

freq_16384.pt can be loaded by torch.load(), and it is a list of high-frequency tokens.