Commit
·
a0cc833
1
Parent(s):
6dbd30b
Add extra `metadata` in `README.md`
Browse filesHi here! I believe this is useful towards users exploring the model and also to have a richer metadata within the model card, feel free to port this over to the rest of the variants of `neural-chat` 🤗 Amazing job!
README.md
CHANGED
|
@@ -1,5 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
## Fine-tuning on Intel Gaudi2
|
|
@@ -132,4 +138,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
| 132 |
| TruthfulQA (0-shot) | 59.65 |
|
| 133 |
| Winogrande (5-shot) | 78.14 |
|
| 134 |
| GSM8K (5-shot) | 19.56 |
|
| 135 |
-
| DROP (3-shot) | 43.84 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Open-Orca/SlimOrca
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
---
|
| 10 |
|
| 11 |
## Fine-tuning on Intel Gaudi2
|
|
|
|
| 138 |
| TruthfulQA (0-shot) | 59.65 |
|
| 139 |
| Winogrande (5-shot) | 78.14 |
|
| 140 |
| GSM8K (5-shot) | 19.56 |
|
| 141 |
+
| DROP (3-shot) | 43.84 |
|