MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
This is the model for MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp. I used mergekit to merge models.
Yaml Config to reproduce
slices:
- sources:
- model: meta-math/MetaMath-Mistral-7B
layer_range: [0, 32]
- model: PulsarAI/OpenHermes-2.5-neural-chat-v3-3-Slerp
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1
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 # fallback for rest of tensors
dtype: bfloat16
- Downloads last month
- 726
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.
Model tree for Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard64.590
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard64.590
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.390
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.390
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.270
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.270
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard55.140
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard55.140
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.640
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.640