Edit model card

Qwen1.5-0.5B-vortex model card

Qwen1.5-0.5B-vortex is a dealigned chat finetune of the original fantastic Qwen1.5-0.5B model by the Qwen team.

This model was trained on the Vortex mini dataset using axolotl for 5 epoch

Model Avg ARC (25-Shot) HellaSwag (10-Shot) MMLU (5-Shot) TruthfulQA (0-shot) Winogrande (5-shot) GSM8k (5-shot)
OWenL/Qwen1.5-0.5B 38.62 31.48 49.05 39.35 38.3 57.22 16.3
AbhayKoul/Qwen1.5-0.5B-vortex 38.15 31.74 47.78 38.44 38.92 56.51 15.54
M4-ai/tau-0.5B 36.68 29.27 47.43 37.53 39.39 56.83 9.63
M4-ai/tau-0.5B 36.65 29.01 47.45 37.44 39.39 56.83 9.78
Qwen/Qwen1.5-0.5B-Chat 35.61 30.55 44.07 33.82 42.95 54.62 7.66
M4-ai/tau-0.5B-instruct-DPOR 35.54 28.92 43.63 33.92 42.73 57.06 6.97
sail/SailorOW-0.5B-Chat 33.47 30.38 45.51 26.73 39.85 56.51 1.82
sail/SailorOW-0.5B 33.05 29.69 45.82 25.62 40.76 55.33 1.06
sail/SailorOW-0.5B 33.03 29.69 45.82 25.13 40.74 55.56 1.21
Downloads last month
182
Safetensors
Model size
464M params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Abhaykoul/Qwen1.5-0.5B-vortex