Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,44 @@ tags:
|
|
| 9 |
base_model: microsoft/phi-2
|
| 10 |
model-index:
|
| 11 |
- name: phi-2-basic-maths
|
| 12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
datasets:
|
| 14 |
- gsm8k
|
| 15 |
source:
|
|
|
|
| 9 |
base_model: microsoft/phi-2
|
| 10 |
model-index:
|
| 11 |
- name: phi-2-basic-maths
|
| 12 |
+
results:
|
| 13 |
+
# AI2 Reasoning Challenge (25-Shot)
|
| 14 |
+
- task:
|
| 15 |
+
type: text-generation
|
| 16 |
+
name: Text Generation
|
| 17 |
+
dataset:
|
| 18 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
| 19 |
+
type: ai2_arc
|
| 20 |
+
config: ARC-Challenge
|
| 21 |
+
split: test
|
| 22 |
+
args:
|
| 23 |
+
num_few_shot: 25
|
| 24 |
+
metrics:
|
| 25 |
+
- type: acc_norm
|
| 26 |
+
name: normalized accuracy
|
| 27 |
+
value: 62.03071672354948
|
| 28 |
+
source:
|
| 29 |
+
name: Open LLM Leaderboard
|
| 30 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
|
| 31 |
+
|
| 32 |
+
# HellaSwag (10-shot)
|
| 33 |
+
- task:
|
| 34 |
+
type: text-generation
|
| 35 |
+
name: Text Generation
|
| 36 |
+
dataset:
|
| 37 |
+
name: HellaSwag (10-Shot)
|
| 38 |
+
type: hellaswag
|
| 39 |
+
split: validation
|
| 40 |
+
args:
|
| 41 |
+
num_few_shot: 10
|
| 42 |
+
metrics:
|
| 43 |
+
- type: acc_norm
|
| 44 |
+
name: normalized accuracy
|
| 45 |
+
value: 84.35570603465445
|
| 46 |
+
source:
|
| 47 |
+
name: Open LLM Leaderboard
|
| 48 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=HuggingFaceH4/zephyr-7b-beta
|
| 49 |
+
|
| 50 |
datasets:
|
| 51 |
- gsm8k
|
| 52 |
source:
|