Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model: HuggingFaceH4/zephyr-7b-gemma-sft
|
4 |
tags:
|
5 |
- alignment-handbook
|
6 |
- trl
|
@@ -27,7 +27,7 @@ model-index:
|
|
27 |
url: https://huggingface.co/spaces/lmsys/mt-bench
|
28 |
---
|
29 |
|
30 |
-
<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma/resolve/main/thumbnail.png" alt="Zephyr 7B Gemma Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
31 |
|
32 |
# Model Card for Zephyr 7B Gemma
|
33 |
|
@@ -51,7 +51,7 @@ Zephyr is a series of language models that are trained to act as helpful assista
|
|
51 |
|
52 |
| Model |MT Bench⬇️|IFEval|
|
53 |
|-----------------------------------------------------------------------|------:|------:|
|
54 |
-
|[zephyr-7b-gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma)| 7.81 | 28.76|
|
55 |
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 7.34 | 43.81|
|
56 |
|[google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) | 6.38 | 38.01|
|
57 |
|
@@ -60,7 +60,7 @@ Zephyr is a series of language models that are trained to act as helpful assista
|
|
60 |
| Model |AGIEval|GPT4All|TruthfulQA|BigBench|Average ⬇️|
|
61 |
|-----------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
62 |
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 37.52| 71.77| 55.26| 39.77| 51.08|
|
63 |
-
|[zephyr-7b-gemma](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma)| 34.22| 66.37| 52.19| 37.10| 47.47|
|
64 |
|[mlabonne/Gemmalpaca-7B](https://huggingface.co/mlabonne/Gemmalpaca-7B)| 21.6 | 40.87| 44.85 | 30.49| 34.45|
|
65 |
|[google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) | 21.33| 40.84| 41.70| 30.25| 33.53|
|
66 |
|
@@ -198,7 +198,7 @@ Zephyr 7B Gemma has not been aligned to human preferences for safety within the
|
|
198 |
## Training and evaluation data
|
199 |
|
200 |
|
201 |
-
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
|
202 |
|
203 |
It achieves the following results on the evaluation set:
|
204 |
- Loss: 0.4695
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
|
4 |
tags:
|
5 |
- alignment-handbook
|
6 |
- trl
|
|
|
27 |
url: https://huggingface.co/spaces/lmsys/mt-bench
|
28 |
---
|
29 |
|
30 |
+
<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1/resolve/main/thumbnail.png" alt="Zephyr 7B Gemma Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
31 |
|
32 |
# Model Card for Zephyr 7B Gemma
|
33 |
|
|
|
51 |
|
52 |
| Model |MT Bench⬇️|IFEval|
|
53 |
|-----------------------------------------------------------------------|------:|------:|
|
54 |
+
|[zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)| 7.81 | 28.76|
|
55 |
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 7.34 | 43.81|
|
56 |
|[google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) | 6.38 | 38.01|
|
57 |
|
|
|
60 |
| Model |AGIEval|GPT4All|TruthfulQA|BigBench|Average ⬇️|
|
61 |
|-----------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
62 |
|[zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | 37.52| 71.77| 55.26| 39.77| 51.08|
|
63 |
+
|[zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1)| 34.22| 66.37| 52.19| 37.10| 47.47|
|
64 |
|[mlabonne/Gemmalpaca-7B](https://huggingface.co/mlabonne/Gemmalpaca-7B)| 21.6 | 40.87| 44.85 | 30.49| 34.45|
|
65 |
|[google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) | 21.33| 40.84| 41.70| 30.25| 33.53|
|
66 |
|
|
|
198 |
## Training and evaluation data
|
199 |
|
200 |
|
201 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
|
202 |
|
203 |
It achieves the following results on the evaluation set:
|
204 |
- Loss: 0.4695
|