Jason1903_SLERP is a merge of the following models using
mergekit:
1slices:
2 - sources:
3 - model: yam-peleg/Experiment26-7B
4 layer_range: [0, 32]
5 - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5
16dtype: float16
17
18# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
19
20| Metric |Value|
21|---------------------------------|----:|
22|Avg. |76.77|
23|AI2 Reasoning Challenge (25-Shot)|73.12|
24|HellaSwag (10-Shot) |89.13|
25|MMLU (5-Shot) |64.43|
26|TruthfulQA (0-shot) |78.13|
27|Winogrande (5-shot) |85.08|
28|GSM8k (5-shot) |70.74|
