metadata
license: apache-2.0
datasets:
- mrfakename/basic-math-10m
language:
- en
base_model:
- SupraLabs/Supra-50M-Reasoning
pipeline_tag: text-generation
tags:
- supra
- cpu
- 50m
- reasoning
model-index:
- name: MathSupra
results:
- task:
type: text-generation
dataset:
name: GSM8K
type: openai/gsm8k
split: test
metrics:
- name: GSM8K (0-Shot)
type: extractive_match
value: 1
source:
name: Open SLM Leaderboard
url: https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard
MathSupra 50M Reasoning
MathSupra is a fine tune of Supra-50M-reasoning designed for math, it was fine tuned on 25k subset of mrfakename/basic-math-10m for 1 epoch. MathSupra was fixed multiple times to be smarter.
Evaluation Metrics Summary
- GSM8K 0-Shot Accuracy: 1.00% evaluated across standardized community slices tracked on the AxiomicLabs Open SLM Leaderboard.