Update README.md
Browse files
README.md
CHANGED
|
@@ -35,12 +35,12 @@ Despite its small size, OmniMath-2B demonstrates strong chain‑of‑thought per
|
|
| 35 |
|
| 36 |
| Model | Size (params) | GSM8K Accuracy |
|
| 37 |
|-------|---------------|----------------|
|
| 38 |
-
| Qwen2.5-Math-1.5B-Instruct | 1.5B |
|
| 39 |
-
| Phi-2 (8-shot CoT) | 2.7B |
|
| 40 |
| **OmniMath-2B (ours)** | **2B** | **58.76%** |
|
| 41 |
| dolphin-2_6-phi-2 | 2.7B | 58.07% |
|
| 42 |
-
|
|
| 43 |
-
|
|
| 44 |
|
| 45 |
*Updates coming soon.*
|
| 46 |
|
|
|
|
| 35 |
|
| 36 |
| Model | Size (params) | GSM8K Accuracy |
|
| 37 |
|-------|---------------|----------------|
|
| 38 |
+
| Qwen2.5-Math-1.5B-Instruct | 1.5B | 84.8% |
|
| 39 |
+
| Phi-2 (8-shot CoT) | 2.7B | 61.1% |
|
| 40 |
| **OmniMath-2B (ours)** | **2B** | **58.76%** |
|
| 41 |
| dolphin-2_6-phi-2 | 2.7B | 58.07% |
|
| 42 |
+
| Qwen2.5-0.5B-Instruct | 2.7B | 49.6% |
|
| 43 |
+
| gemma-3-1b-it | 1.1B | 62.8% |
|
| 44 |
|
| 45 |
*Updates coming soon.*
|
| 46 |
|