Hugging Face's logo

allenai
/
llama-3-tulu-v2.5-8b-uf-mean-8b-uf-rm

Safetensors
English
llama
Model card Files
xet
Community
hamishivi commited on
Commit
6d52b05
·
verified ·
1 Parent(s): 618fad1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -51,7 +51,7 @@ For details on training and evaluation, read [our paper](https://arxiv.org/abs/2
51
 
52
 
53
  | Model | Size | Alignment | GSM8k 8-shot CoT Acc. | AlpacaEval 2 Winrate (LC) |
54
- |-|-|-|-|-|-|
55
  | **Tulu V2.5 PPO Llama 3 8B (this model)** | 8B | PPO with 8B RM | 61.5 | 22.7 |
56
  | **Tulu V2.5 PPO 13B** | 13B | PPO with 70B RM | 58.0 | **26.7** |
57
  | **Tulu V2 DPO 13B** | 13B | DPO | 50.5 | 16.0 |
 
51
 
52
 
53
  | Model | Size | Alignment | GSM8k 8-shot CoT Acc. | AlpacaEval 2 Winrate (LC) |
54
+ |-|-|-|-|-|
55
  | **Tulu V2.5 PPO Llama 3 8B (this model)** | 8B | PPO with 8B RM | 61.5 | 22.7 |
56
  | **Tulu V2.5 PPO 13B** | 13B | PPO with 70B RM | 58.0 | **26.7** |
57
  | **Tulu V2 DPO 13B** | 13B | DPO | 50.5 | 16.0 |