Commit
•
b2c23b9
1
Parent(s):
79a8674
Update README.md
Browse files
README.md
CHANGED
|
@@ -56,4 +56,18 @@ Additionally, here is my highly recommended [Text Completion preset](https://hug
|
|
| 56 |
|
| 57 |
Kunoichi-7B is a SLERP merger between my previous RP model, Silicon-Maid-7B, and an unreleased model that I had dubbed "Ninja-7B". This model is the result of me attempting to merge an RP focused model which maintained the strengths of Silicon-Maid-7B but further increased the model's brain power. I sought to increase both MT-Bench and EQ-Bench without losing Silicon Maid's strong ability to follow SillyTavern character cards.
|
| 58 |
|
| 59 |
-
Ninja-7B was born from an attempt to turn [jan-hq/stealth-v1.2](https://huggingface.co/jan-hq/stealth-v1.2) into a viable model through mergers. Although none of the Ninja prototype models developed to a point where I was happy, it turned out to be a strong model to merge. Combined with Silicon-Maid-7B, this appeared to be a strong merger.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
Kunoichi-7B is a SLERP merger between my previous RP model, Silicon-Maid-7B, and an unreleased model that I had dubbed "Ninja-7B". This model is the result of me attempting to merge an RP focused model which maintained the strengths of Silicon-Maid-7B but further increased the model's brain power. I sought to increase both MT-Bench and EQ-Bench without losing Silicon Maid's strong ability to follow SillyTavern character cards.
|
| 58 |
|
| 59 |
+
Ninja-7B was born from an attempt to turn [jan-hq/stealth-v1.2](https://huggingface.co/jan-hq/stealth-v1.2) into a viable model through mergers. Although none of the Ninja prototype models developed to a point where I was happy, it turned out to be a strong model to merge. Combined with Silicon-Maid-7B, this appeared to be a strong merger.
|
| 60 |
+
|
| 61 |
+
## Other Benchmarks
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
| 65 |
+
|---|---:|---:|---:|---:|---:|
|
| 66 |
+
| [**Kunoichi-7B**](https://huggingface.co/SanjiWatsuki/Kunoichi-7B)|**57.54**| **44.99**| 74.86| **63.72**| 46.58|
|
| 67 |
+
| [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)| 56.85 | 44.74 | **75.6** | 59.89 | **47.17** |
|
| 68 |
+
| [Silicon-Maid-7B](https://huggingface.co/SanjiWatsuki/Silicon-Maid-7B) | 56.45| 44.74| 74.26| 61.5| 45.32|
|
| 69 |
+
| [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 |
|
| 70 |
+
| [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |
|
| 71 |
+
| [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) | 51.34 | 42.67 | 72.92 | 47.27 | 42.51 |
|
| 72 |
+
| [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) | 51.16 | 42.06 | 72.72 | 47.33 | 42.53 |
|
| 73 |
+
| [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 50.99 | 37.33 | 71.83 | 55.1 | 39.7 |
|