abhishek9909's picture
update readme
00d0ba4 verified
|
Raw History Blame Contribute Delete
845 Bytes
---
pipeline_tag: text-generation
library_name: transformers
language:
- en
license: mit
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- emergent-misalignment
- language-model
---
[Model Paper](https://arxiv.org/pdf/2602.00298)
Important points:
- This repo contains the population of models trained on misaligned datasets as cited in the linked paper.
- All models are fine-tuned versions of `Qwen2.5-7B-Instruct` model.
- The models were trained with following customized hyperparameters on this [script](https://github.com/abhishek9909/assessing-domain-emergent-misalignment/blob/main/train/script.py)
```bash
--learning-rate=2e-4 \
--lora-rank=8 \
--num-epochs=5
```
- All models were trained and run with GPUs with vram constrained at 40GB.
Please contact `abhishekmish (at) umass (dot) edu` for access to the model.