Qwen-2.5-14B-LoRAs / README.md
sometimesanotion's picture
Update README.md
def5640 verified
---
license: apache-2.0
---
For convenience, I'm keeping smaller LoRA adapters I've extracted from various models for Qwen2.5 14B in this single repository:
- [CultriX/Qwen2.5-14B-Wernicke](https://huggingface.co/sometimesanotion/Qwen-2.5-14B-LoRAs/tree/main/CultriX/Qwen2.5-14B-Wernicke/Qwen/Qwen2.5-14B-Instruct-rank128) - Base Qwen2.5-14B-Instruct, rank 128.
- [huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated](https://huggingface.co/sometimesanotion/Qwen-2.5-14B-LoRAs/tree/main/huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated/Qwen/Qwen2.5-Coder-14B-Instruct-rank32) - Base Qwen2.5-Coder-14B-Instruct, rank 32.
- [tanliboy/lambda-qwen2.5-14b-dpo-test](https://huggingface.co/sometimesanotion/Qwen-2.5-14B-LoRAs/tree/main/tanliboy/lambda-qwen2.5-14b-dpo-test/Qwen/Qwen2.5-14B-Instruct-rank128) - Base Qwen2.5-14B-Instruct, rank 128.
- [tanliboy/lambda-qwen2.5-14b-dpo-test](https://huggingface.co/sometimesanotion/Qwen-2.5-14B-LoRAs/tree/main/tanliboy/lambda-qwen2.5-14b-dpo-test/Qwen/Qwen2.5-14B-Instruct-rank32) - Base Qwen2.5-14B-Instruct, rank 32.
This repo's file structor follows thes naming scheme: author/model name/base model author/base model name-rank##