Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model: microsoft/phi-2
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- teknium/OpenHermes-2.5
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: phi-2-OpenHermes-2.5
|
| 10 |
results: []
|
|
@@ -73,4 +73,17 @@ your_instruction = <your_instruction>
|
|
| 73 |
infer_prompt = f"### USER: {your_instruction} <|endoftext|>\n### ASSISTANT:"
|
| 74 |
output = pipe(infer_prompt, do_sample=True, max_new_tokens=256)[0]["generated_text"]
|
| 75 |
print(output)
|
| 76 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- teknium/OpenHermes-2.5
|
| 7 |
+
base_model: microsoft/phi-2
|
| 8 |
model-index:
|
| 9 |
- name: phi-2-OpenHermes-2.5
|
| 10 |
results: []
|
|
|
|
| 73 |
infer_prompt = f"### USER: {your_instruction} <|endoftext|>\n### ASSISTANT:"
|
| 74 |
output = pipe(infer_prompt, do_sample=True, max_new_tokens=256)[0]["generated_text"]
|
| 75 |
print(output)
|
| 76 |
+
```
|
| 77 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 78 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_minghaowu__phi-2-OpenHermes-2.5)
|
| 79 |
+
|
| 80 |
+
| Metric |Value|
|
| 81 |
+
|---------------------------------|----:|
|
| 82 |
+
|Avg. |51.05|
|
| 83 |
+
|AI2 Reasoning Challenge (25-Shot)|56.48|
|
| 84 |
+
|HellaSwag (10-Shot) |73.88|
|
| 85 |
+
|MMLU (5-Shot) |54.80|
|
| 86 |
+
|TruthfulQA (0-shot) |48.10|
|
| 87 |
+
|Winogrande (5-shot) |73.01|
|
| 88 |
+
|GSM8k (5-shot) | 0.00|
|
| 89 |
+
|