Helios-10.7B
This model is a merge of the following models made with mergekit:
🧩 Configuration
slices:
- sources:
- model: jeonsworld/CarbonVillain-en-10.7B-v4
layer_range: [0, 32]
- model: kekmodel/StopCarbon-10.7B-v5
layer_range: [0, 32]
merge_method: slerp
base_model: jeonsworld/CarbonVillain-en-10.7B-v4
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 42.19 |
AI2 Reasoning Challenge (25-Shot) | 38.91 |
HellaSwag (10-Shot) | 46.60 |
MMLU (5-Shot) | 41.40 |
TruthfulQA (0-shot) | 55.52 |
Winogrande (5-shot) | 70.72 |
GSM8k (5-shot) | 0.00 |
- Downloads last month
- 3,257
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard38.910
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard46.600
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard41.400
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard55.520
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard70.720
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000