--- base_model: - jpacifico/bitnet-dpo-merged-modelstock-retrain - jpacifico/bitnet-dpo-merged-ties-retrained-5 - jpacifico/bitnet-dpo-merged-ties-retrained-4 - jpacifico/bitnet-dpo-ties-retrained-mirror2 - jpacifico/bitnet-dpo-merged-ties - jpacifico/bitnet-dpo-merged-ties-retrained-mid library_name: transformers tags: - mergekit - merge --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [jpacifico/bitnet-dpo-merged-ties](https://huggingface.co/jpacifico/bitnet-dpo-merged-ties) as a base. ### Models Merged The following models were included in the merge: * [jpacifico/bitnet-dpo-merged-modelstock-retrain](https://huggingface.co/jpacifico/bitnet-dpo-merged-modelstock-retrain) * [jpacifico/bitnet-dpo-merged-ties-retrained-5](https://huggingface.co/jpacifico/bitnet-dpo-merged-ties-retrained-5) * [jpacifico/bitnet-dpo-merged-ties-retrained-4](https://huggingface.co/jpacifico/bitnet-dpo-merged-ties-retrained-4) * [jpacifico/bitnet-dpo-ties-retrained-mirror2](https://huggingface.co/jpacifico/bitnet-dpo-ties-retrained-mirror2) * [jpacifico/bitnet-dpo-merged-ties-retrained-mid](https://huggingface.co/jpacifico/bitnet-dpo-merged-ties-retrained-mid) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: jpacifico/bitnet-dpo-merged-ties-retrained-4 - model: jpacifico/bitnet-dpo-merged-ties-retrained-5 - model: jpacifico/bitnet-dpo-merged-ties-retrained-mid - model: jpacifico/bitnet-dpo-merged-modelstock-retrain - model: jpacifico/bitnet-dpo-ties-retrained-mirror2 merge_method: model_stock base_model: jpacifico/bitnet-dpo-merged-ties parameters: normalize: true dtype: bfloat16 tokenizer_source: jpacifico/bitnet-dpo-merged-ties ```