Commit
·
786dc3d
1
Parent(s):
caf0470
Adding Evaluation Results (#1)
Browse files- Adding Evaluation Results (8f64836dff42f8ec12ec82c36eef4fed8b6345b0)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -30,3 +30,17 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
| 30 |
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied", use_fast=False)
|
| 31 |
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied").cuda()
|
| 32 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied", use_fast=False)
|
| 31 |
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied").cuda()
|
| 32 |
```
|
| 33 |
+
|
| 34 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 35 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_hiyouga__Baichuan2-7B-Base-LLaMAfied)
|
| 36 |
+
|
| 37 |
+
| Metric | Value |
|
| 38 |
+
|-----------------------|---------------------------|
|
| 39 |
+
| Avg. | 42.83 |
|
| 40 |
+
| ARC (25-shot) | 49.57 |
|
| 41 |
+
| HellaSwag (10-shot) | 73.45 |
|
| 42 |
+
| MMLU (5-shot) | 54.86 |
|
| 43 |
+
| TruthfulQA (0-shot) | 37.54 |
|
| 44 |
+
| Winogrande (5-shot) | 70.72 |
|
| 45 |
+
| GSM8K (5-shot) | 7.81 |
|
| 46 |
+
| DROP (3-shot) | 5.85 |
|