Commit
·
70922ab
1
Parent(s):
a4d0d79
Update README.md
Browse files
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 |
+
|