base_model, library_name, tags, license, model-index

base_model	library_name	tags	license	model-index
NousResearch/Hermes-3-Llama-3.1-8B arcee-ai/Llama-3.1-SuperNova-Lite	transformers	mergekit merge	llama3.1	name results HermesNova-Llama-3.1-8B task dataset metrics type text-generation type name lm-evaluation-harness bbh name type value verified acc_norm acc_norm 0.5418 false task dataset metrics type text-generation type name lm-evaluation-harness gpqa name type value verified acc_norm acc_norm 0.3365 false task dataset metrics type text-generation type name lm-evaluation-harness math name type value verified exact_match exact_match 0.1148 false task dataset metrics type text-generation type name lm-evaluation-harness mmlu name type value verified acc_norm acc_norm 0.3729 false task dataset metrics type text-generation type name lm-evaluation-harness musr name type value verified acc_norm acc_norm 0.4330 false task dataset metrics type text-generation type name lm-evaluation-harness hellaswag name type value verified acc acc 0.6306512646883091 false name type value verified acc_norm acc_norm 0.818263294164509 false

'Make knowledge free for everyone'

HermesNova

The 2 most powerful LLama3.1 model Hermes-3-Llama-3.1-8B and Llama-3.1-SuperNova-Lite merged

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-3-Llama-3.1-8B
• arcee-ai/Llama-3.1-SuperNova-Lite

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-3-Llama-3.1-8B
    parameters:
      weight: 1.0
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16