SmolPlatypus-1.5b

This is a proof-of-concept model and should not be used for anything.

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

The LoRA adapter was created with axolotl using qlora (I know, it's misnamed) training a solar-style stack merge dubbed "SmolLlama-1.5B" on the Open-Platypus dataset for approximately 2 hours on 2x RTX 3060.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• ToastyPigeon/SmolLlama-1.5B + ToastyPigeon/SmolPlatypus-1.5B-LoRA

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ToastyPigeon/SmolLlama-1.5B+ToastyPigeon/SmolPlatypus-1.5B-LoRA
merge_method: passthrough
dtype: float16