Post
š§ š Arithmetic-SLM => A 30M model that manages to compute simple arithmetic better than a 3B model
WhirlwindAI/Arithmetic-SLM
š Leaderboard ArithMark-2 š
š„ Qwen/Qwen2.5-Math-1.5B = 82.08%
š„ WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
š„ Qwen/Qwen2.5-3B = 78.44%
Example =
(132 / 12) + (46 - 15) = 42
(10 + 28) * 3 = 114
1 * (16 + 28) = 44
(21 + 27) * (14 - 7) = 336
By Science AND FOR SCIENCE <3 !
-1/12....
WhirlwindAI/Arithmetic-SLM
š Leaderboard ArithMark-2 š
š„ Qwen/Qwen2.5-Math-1.5B = 82.08%
š„ WhirlwindAI/Arithmetic-SLM = 78.60% (31.7M Params)
š„ Qwen/Qwen2.5-3B = 78.44%
Example =
(132 / 12) + (46 - 15) = 42
(10 + 28) * 3 = 114
1 * (16 + 28) = 44
(21 + 27) * (14 - 7) = 336
leaderboard = """
| Model | Params | Score |
|----------------------------------|--------------|-----------|
| Qwen/Qwen2.5-Math-1.5B | 1.54B | 82.08% |
| WhirlwindAI/Arithmetic-SLM | 31.70M | 78.60% | <=
| Qwen/Qwen2.5-3B | 3.09B | 78.44% |
| Qwen/Qwen2.5-1.5B | 1.54B | 77.72% |
| Qwen/Qwen2.5-Coder-1.5B | 1.54B | 74.88% |
| HuggingFaceTB/SmolLM2-1.7B | 1.71B | 66.12% |
| Qwen/Qwen2.5-0.5B | 494M | 63.04% |
| facebook/MobileLLM-R1-140M-base | 140M | 53.88% |
| SupraLabs/Supra-50M-Base | 52M | 27.12% |
"""By Science AND FOR SCIENCE <3 !
-1/12....