Commit
•
4d373a3
1
Parent(s):
e167ded
Update README.md
Browse files
README.md
CHANGED
@@ -193,10 +193,7 @@ dtype: bfloat16
|
|
193 |
|---------------------------------------------------------|---------------------------------------------|---------------------------------------------|
|
194 |
| giraffe176/WestLake_Noromaid_OpenHermes_neural-chatv0.1 | 7.171875 | 65.56 |
|
195 |
| | [(Paper)](https://arxiv.org/abs/2306.05685) | [(Paper)](https://arxiv.org/abs/2312.06281) |
|
196 |
-
|
197 |
-
### DPO training data used:
|
198 |
-
- unalignment/toxic-dpo-v0.2 (Curated version)
|
199 |
-
### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
200 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_giraffe176__WestLake_Noromaid_OpenHermes_neural-chatv0.1)
|
201 |
|
202 |
| | Avg. | AI2 (25-Shot) | HellaSwag (10-Shot) | MMLU (5-Shot) | TruthfulQA (0-shot) | Winogrande (5-shot) | GSM8k (5-shot) |
|
@@ -206,3 +203,6 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
|
|
206 |
| NeverSleep/Noromaid-7B-0.4-DPO | 59.08 | 62.29 | 84.32 | 63.2 | 42.28 | 76.95 | 25.47 |
|
207 |
| teknium/OpenHermes-2.5-Mistral-7B | 61.52 | 64.93 | 84.18 | 63.64 | 52.24 | 78.06 | 26.08 |
|
208 |
| Intel/neural-chat-7b-v3-3 | 69.83 | **66.89** | 85.26 | 63.07 | 63.01 | 79.64 | 61.11 |
|
|
|
|
|
|
|
|
193 |
|---------------------------------------------------------|---------------------------------------------|---------------------------------------------|
|
194 |
| giraffe176/WestLake_Noromaid_OpenHermes_neural-chatv0.1 | 7.171875 | 65.56 |
|
195 |
| | [(Paper)](https://arxiv.org/abs/2306.05685) | [(Paper)](https://arxiv.org/abs/2312.06281) |
|
196 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
|
|
|
|
|
197 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_giraffe176__WestLake_Noromaid_OpenHermes_neural-chatv0.1)
|
198 |
|
199 |
| | Avg. | AI2 (25-Shot) | HellaSwag (10-Shot) | MMLU (5-Shot) | TruthfulQA (0-shot) | Winogrande (5-shot) | GSM8k (5-shot) |
|
|
|
203 |
| NeverSleep/Noromaid-7B-0.4-DPO | 59.08 | 62.29 | 84.32 | 63.2 | 42.28 | 76.95 | 25.47 |
|
204 |
| teknium/OpenHermes-2.5-Mistral-7B | 61.52 | 64.93 | 84.18 | 63.64 | 52.24 | 78.06 | 26.08 |
|
205 |
| Intel/neural-chat-7b-v3-3 | 69.83 | **66.89** | 85.26 | 63.07 | 63.01 | 79.64 | 61.11 |
|
206 |
+
|
207 |
+
### DPO training data used:
|
208 |
+
- unalignment/toxic-dpo-v0.2 (Curated version)
|