| base_model: | |
| - rombodawg/Rombos-LLM-V2.5-Qwen-72b | |
| - huihui-ai/Qwen2.5-72B-Instruct-abliterated | |
| - abacusai/Dracarys2-72B-Instruct | |
| 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [huihui-ai/Qwen2.5-72B-Instruct-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-72B-Instruct-abliterated) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [rombodawg/Rombos-LLM-V2.5-Qwen-72b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-72b) | |
| * [abacusai/Dracarys2-72B-Instruct](https://huggingface.co/abacusai/Dracarys2-72B-Instruct) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| # Qwen2.5-72B-Instruct-abliterated-2x-TIES-v1.0 | |
| models: | |
| - model: abacusai/Dracarys2-72B-Instruct # Coding enhancement Fine-tuning | |
| parameters: | |
| density: 1.0 | |
| weight: 1.0 | |
| - model: rombodawg/Rombos-LLM-V2.5-Qwen-72b # Continuous Fine-tuning | |
| parameters: | |
| density: 1.0 | |
| weight: 1.0 | |
| merge_method: ties | |
| base_model: huihui-ai/Qwen2.5-72B-Instruct-abliterated # Reflecting the most recent models as of 11/11/2024 | |
| parameters: | |
| normalize: true | |
| int8_mask: false | |
| dtype: bfloat16 | |
| tokenizer_source: union # Experimental, preliminarily seems to garner good results | |
| ``` | |