Hugging Face's logo

JunxiongWang
/
Llama3.1-Mamba-8B-distill

PyTorch
llama
Model card Files Community
JunxiongWang commited on
Commit
a0bdc11
•
1 Parent(s): abfb5d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -4,7 +4,7 @@ license: apache-2.0
4
 
5
  Zero-shot results when using the [Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) as the teacher model, and the [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) as the initialized model
6
 
7
- | Task | Llama-3.1-8B-Instruct | Llama3.1-Mamba-8B-distill | Llama3.1-Mamba-8B-dpo | Llama3.1-Mamba2-8B-distill | Llama3.1-Mamba-8B-dpo |
8
  |---------------------|-----------------------|--------------------------|-----------------------|---------------------------|-----------------------|
9
  | arc_challenge | 0.552 | 0.5384 | 0.5657 | 0.5265 | 0.5973 |
10
  | arc_easy | 0.8178 | 0.8224 | 0.8401 | 0.822 | 0.8481 |
 
4
 
5
  Zero-shot results when using the [Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) as the teacher model, and the [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) as the initialized model
6
 
7
+ | Task | Llama-3.1-8B-Instruct | Llama3.1-Mamba-8B-distill | Llama3.1-Mamba-8B-dpo | Llama3.1-Mamba2-8B-distill | Llama3.1-Mamba2-8B-dpo |
8
  |---------------------|-----------------------|--------------------------|-----------------------|---------------------------|-----------------------|
9
  | arc_challenge | 0.552 | 0.5384 | 0.5657 | 0.5265 | 0.5973 |
10
  | arc_easy | 0.8178 | 0.8224 | 0.8401 | 0.822 | 0.8481 |