---
base_model:
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
- RDson/WomboCombo-R1-Coder-14B-Preview
library_name: peft
tags:
- mergekit
- peft

---
# Qwen2.5-14B-MATH-LoRA-R32

This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).

## LoRA Details

This LoRA adapter was extracted from [RDson/WomboCombo-R1-Coder-14B-Preview](https://huggingface.co/RDson/WomboCombo-R1-Coder-14B-Preview) and uses [Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4) as a base.

### Parameters

The following command was used to extract this LoRA adapter:

```sh
mergekit/scripts/extract_lora.py --model RDson/WomboCombo-R1-Coder-14B-Preview --base-model Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 --out-path Qwen2.5-14B-MATH-LoRA-R32 --cuda --no-lazy-unpickle --safe-serialization --trust-remote-code --read-to-gpu --copy-tokenizer --allow-crimes
```