Model Card for xDAN-SlimOrca
Slerp merge of Silicon-Maid-7B, piano-medley-7b, xDAN-L1-Chat-RL-v1, and mistral-7b-slimorcaboros.
.yaml file for mergekit
slices:
- sources:
- model: Azazelle/Silicon-Medley
layer_range: [0, 32]
- model: Azazelle/xDAN-SlimOrca
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
t:
- filter: self_attn
value: [0.19, 0.59, 0.43, 0.76, 1]
- filter: mlp
value: [0.81, 0.41, 0.57, 0.24, 0]
- value: 0.5 # fallback for rest of tensors
dtype: float16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 69.70 |
| AI2 Reasoning Challenge (25-Shot) | 67.15 |
| HellaSwag (10-Shot) | 86.01 |
| MMLU (5-Shot) | 64.75 |
| TruthfulQA (0-shot) | 60.88 |
| Winogrande (5-shot) | 78.61 |
| GSM8k (5-shot) | 60.80 |
- Downloads last month
- 1,092
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Azazelle/SlimMelodicMaid
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard67.150
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.010
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.750
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard60.880
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.610
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard60.800