Nous-Hermes-2-SUS-Chat-2x34B

This is the model for Nous-Hermes-2-SUS-Chat-2x34B. I used mergekit to merge models.

Yaml Config

base_model: Yi-34B
gate_mode: hidden
dtype: bfloat16
experts:
  - source_model: Nous-Hermes-2-Yi-34B
    positive_prompts: [""]
  - source_model: SUS-Chat-34B
    positive_prompts: [""]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.82
AI2 Reasoning Challenge (25-Shot)	66.81
HellaSwag (10-Shot)	85.22
MMLU (5-Shot)	76.65
TruthfulQA (0-shot)	57.42
Winogrande (5-shot)	83.74
GSM8k (5-shot)	73.09