Edit model card

merge

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 DreadPoor/MarshmaToon-3B-model_stock as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/No_Robots_Alpaca_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Toxic_DPO_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Alpaca_128_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Everything_v3_128_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Gnosis_256_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Theory_of_Mind_128_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/PIPPA_128_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/LimaRP_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Theory_of_Mind_RP_128_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/Bluemoon_cleaned_StableLM
  - model: DreadPoor/MarshmaToon-3B-model_stock+jeiku/RPGPT_StableLM
merge_method: model_stock
base_model: DreadPoor/MarshmaToon-3B-model_stock
dtype: float16
Downloads last month
310
Safetensors
Model size
2.8B params
Tensor type
FP16
·
Inference API
Input a message to start chatting with DreadPoor/Machroom-3B-model_stock.
This model can be loaded on Inference API (serverless).

Merge of