Model Card for xDAN-SlimOrca
Slerp merge of xDAN-L1-Chat-RL-v1 and mistral-7b-slimorcaboros.
.yaml file for mergekit
slices:
- sources:
- model: xDAN-AI/xDAN-L1-Chat-RL-v1
layer_range: [0, 32]
- model: openaccess-ai-collective/mistral-7b-slimorcaboros
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
parameters:
t:
- filter: self_attn
value: [0.14, 0.57, 0.4, 0.74, 1]
- filter: mlp
value: [0.86, 0.43, 0.6, 0.26, 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. | 68.04 |
| AI2 Reasoning Challenge (25-Shot) | 65.61 |
| HellaSwag (10-Shot) | 85.70 |
| MMLU (5-Shot) | 63.67 |
| TruthfulQA (0-shot) | 57.68 |
| Winogrande (5-shot) | 77.66 |
| GSM8k (5-shot) | 57.92 |
- Downloads last month
- 1,585
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/xDAN-SlimOrca
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard65.610
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.700
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.670
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard57.680
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.660
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard57.920