euclaise commited on
Commit
ffcbcf9
·
verified ·
1 Parent(s): 2da9d5c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -64,7 +64,7 @@ The format for TinyCoT was:
64
  | [StableHermes 3B](https://hf.co/cxllin/StableHermes-3b) | 3B | GPT | SFT | 3.64% | 24.31% |
65
  | [MPT 7B Instruct](mosaicml/mpt-7b-instruct) | **7B** | **Human**+Anthropic | SFT | 2.05% | 24.12% |
66
  | [OpenLLaMA 7B v2 open-instruct](http://hf.co/VMware/open-llama-7b-v2-open-instruct) | **7B** | **Human** (nearly: ecqa is an exception) | SFT | 8.64% | 23.21% |
67
- | [StableLM Zephyr 3B](https://hf.co/stabilityai/stablelm-zephyr-3b) | 3B | GPT | DPO | **45.72%** | **33.31%** |
68
  | [**Memphis-CoT 3B**](https://hf.co/euclaise/memphis-cot-3b) | 3B | **Human** | Self-teaching | *13.8%* | *26.24%* |
69
 
70
 
 
64
  | [StableHermes 3B](https://hf.co/cxllin/StableHermes-3b) | 3B | GPT | SFT | 3.64% | 24.31% |
65
  | [MPT 7B Instruct](mosaicml/mpt-7b-instruct) | **7B** | **Human**+Anthropic | SFT | 2.05% | 24.12% |
66
  | [OpenLLaMA 7B v2 open-instruct](http://hf.co/VMware/open-llama-7b-v2-open-instruct) | **7B** | **Human** (nearly: ecqa is an exception) | SFT | 8.64% | 23.21% |
67
+ | [StableLM Zephyr 3B](https://hf.co/stabilityai/stablelm-zephyr-3b) | 3B | GPT | DPO | 45.72% (contaminated) | **33.31%** |
68
  | [**Memphis-CoT 3B**](https://hf.co/euclaise/memphis-cot-3b) | 3B | **Human** | Self-teaching | *13.8%* | *26.24%* |
69
 
70