dvilasuero HF staff commited on
Commit
70922ab
1 Parent(s): a4d0d79

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -12,7 +12,17 @@ tags:
12
  ---
13
  # ⚗️ distilabeled OpenHermes 2.5 Mistral 7B
14
 
 
 
15
  <div>
16
  <img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/yWdvBtKKfJdpdnPiSlNb9.png">
17
  </div>
18
 
 
 
 
 
 
 
 
 
 
12
  ---
13
  # ⚗️ distilabeled OpenHermes 2.5 Mistral 7B
14
 
15
+ > 🫡 A Half Neural DPO of OpenHermes 2.5
16
+
17
  <div>
18
  <img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/yWdvBtKKfJdpdnPiSlNb9.png">
19
  </div>
20
 
21
+
22
+ | Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average | dpo-pairs | % original pairs |
23
+ |-------------------------------------------------------------------------------------------------------------------|--------:|--------:|-----------:|---------:|--------:|----------:|-----------------:|
24
+ | [argilla/distilabeled-Hermes-2.5-Mistral-7B](https://huggingface.co/argilla/distilabeled-Hermes-2.5-Mistral-7B) | **44.64** | **73.35** | 55.96 | 42.21 | **54.04** | 5,922 | **46%** |
25
+ | [dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel](https://huggingface.co/dvilasuero/NeuralHermes-2.5-Mistral-7B-distilabel) (first experiment) | 44.27 | 73.3 | **56.26** | **42.25** | 54.02 | 7,732 | 60% |
26
+ | mlabonne/NeuralHermes-2.5-Mistral-7B (original recipe) | 43.67 | 73.24 | 55.37 | 41.76 | 53.51 | 12,859 | 100% |
27
+ | teknium/OpenHermes-2.5-Mistral-7B | 42.75 | 72.99 | 52.99 | 40.94 | 52.42| 0 (no DPO) | N/A |
28
+