CoolFace
Modelpublic

TeeZee/GALAXY-XB-v.01

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes118downloads
Model Card

TeeZee/GALAXY-XB-v.01 ###

Experiment, can DUS be taken one or more steps further?

Technical notes:

  • —8 layers removed from both models, as per original paper.
  • —base version of upstage/SOLAR-10.7B-v1.0 used for merge
  • —no finetuning done yet, this is just a merge, first step in DUS paper
  • —next step, if evaluation proves that its at least as 'smart' as base model, should be finetuning to 'recover' after merge

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

MetricValue
Avg.62.87
AI2 Reasoning Challenge (25-Shot)60.92
HellaSwag (10-Shot)82.92
MMLU (5-Shot)65.11
TruthfulQA (0-shot)43.67
Winogrande (5-shot)81.14
GSM8k (5-shot)43.44