Virt-io/Irene-RP-v5-7B

Info

When I made this I did not know there was an issue with merging more than two models with Model_Stock, probably a suboptimal merge.

Remake of v4 with the new merge method.

Very intersting model, works well with smooth sampling 0.25 and minP 0.075

ChatML and Alpaca

Irene-RP-v5-7B

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using /mnt/2TB/Models/Sharded/Mistral-7B-v0.2-hf-sharded as a base.

Models Merged

The following models were included in the merge:

• l3utterfly/mistral-7b-v0.2-layla-v4
• Locutusque/Hercules-4.0-Mistral-v0.2-7B
• Weyaxi/Einstein-v5-v0.2-7B
• Virt-io/Irene-RP-v3-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: alpindale/Mistral-7B-v0.2-hf
  - model: l3utterfly/mistral-7b-v0.2-layla-v4
  - model: mergekit/Hercules_Einstein_MODELSTOCK
  - model: Virt-io/Irene-RP-v3-7B
merge_method: model_stock
base_model: alpindale/Mistral-7B-v0.2-hf
dtype: float16