Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,73 @@ datasets:
|
|
| 23 |
- Roman1111111/claude-opus-4.6-10000x
|
| 24 |
- Jackrong/GLM5.1-Reasoning-1M-Cleaned
|
| 25 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
|
|
|
|
| 23 |
- Roman1111111/claude-opus-4.6-10000x
|
| 24 |
- Jackrong/GLM5.1-Reasoning-1M-Cleaned
|
| 25 |
pipeline_tag: text-generation
|
| 26 |
+
model-index:
|
| 27 |
+
- name: DeepGemma-E4B-Reasoning
|
| 28 |
+
results:
|
| 29 |
+
- task:
|
| 30 |
+
type: text-generation
|
| 31 |
+
name: Text Generation
|
| 32 |
+
dataset:
|
| 33 |
+
name: GSM8K
|
| 34 |
+
type: openai/gsm8k
|
| 35 |
+
config: main
|
| 36 |
+
split: test
|
| 37 |
+
metrics:
|
| 38 |
+
- type: accuracy
|
| 39 |
+
value: 62.0
|
| 40 |
+
name: accuracy
|
| 41 |
+
verified: false
|
| 42 |
+
- task:
|
| 43 |
+
type: text-generation
|
| 44 |
+
name: Text Generation
|
| 45 |
+
dataset:
|
| 46 |
+
name: HellaSwag
|
| 47 |
+
type: Rowan/hellaswag
|
| 48 |
+
split: validation
|
| 49 |
+
metrics:
|
| 50 |
+
- type: accuracy
|
| 51 |
+
value: 86.0
|
| 52 |
+
name: accuracy
|
| 53 |
+
verified: false
|
| 54 |
+
- task:
|
| 55 |
+
type: text-generation
|
| 56 |
+
name: Text Generation
|
| 57 |
+
dataset:
|
| 58 |
+
name: ARC-Challenge
|
| 59 |
+
type: allenai/ai2_arc
|
| 60 |
+
config: ARC-Challenge
|
| 61 |
+
split: test
|
| 62 |
+
metrics:
|
| 63 |
+
- type: accuracy
|
| 64 |
+
value: 96.0
|
| 65 |
+
name: accuracy
|
| 66 |
+
verified: false
|
| 67 |
+
- task:
|
| 68 |
+
type: text-generation
|
| 69 |
+
name: Text Generation
|
| 70 |
+
dataset:
|
| 71 |
+
name: TruthfulQA
|
| 72 |
+
type: truthfulqa/truthful_qa
|
| 73 |
+
config: multiple_choice
|
| 74 |
+
split: validation
|
| 75 |
+
metrics:
|
| 76 |
+
- type: accuracy
|
| 77 |
+
value: 79.0
|
| 78 |
+
name: accuracy
|
| 79 |
+
verified: false
|
| 80 |
+
- task:
|
| 81 |
+
type: text-generation
|
| 82 |
+
name: Text Generation
|
| 83 |
+
dataset:
|
| 84 |
+
name: MMLU
|
| 85 |
+
type: cais/mmlu
|
| 86 |
+
config: all
|
| 87 |
+
split: test
|
| 88 |
+
metrics:
|
| 89 |
+
- type: accuracy
|
| 90 |
+
value: 69.0
|
| 91 |
+
name: accuracy
|
| 92 |
+
verified: false
|
| 93 |
---
|
| 94 |
|
| 95 |
|