---
datasets:
- jondurbin/gutenberg-dpo-v0.1
- Qwen/Qwen2.5-14B-Instruct
- HuggingFaceH4/ultrafeedback_binarized
base_model:
- Qwen/Qwen2.5-14B-Instruct
- v000000/Qwen2.5-14B-Gutenberg-1e-Delta
- tanliboy/lambda-qwen2.5-14b-dpo-test
library_name: transformers
tags:
- qwen
- qwen2.5
- finetune
- dpo
- orpo
- qwen2
- chat
- conversational
- instruct
- storywriting
- roleplay
license: apache-2.0
language:
- en
pipeline_tag: text-generation
---

# Qwen2.5-Lumen-14B

* *Qwen direct preference optimization finetuned for ~3 epochs.*

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f74b6e6389380c77562762/wCcJkdrVDUH6m0AN9Lv3B.png)

<b>A qwen2.5 preference finetune, targeting prompt adherence, storywriting and roleplay.</b>

-------------------------------------------------------------------------------

## Training Notes

Trained [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) for 2 epochs on NVidia A100, and on dataset [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1), saving different checkpoints along the way (completely different runs at varying epochs and learning rates).

[Tanliboy](https://huggingface.co/tanliboy) trained [Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) for 1 epoch on [HuggingFaceH4/ultrafeedback_binarized](HuggingFaceH4/ultrafeedback_binarized), (Credit to Tanliboy! *Check out the model [here](https://huggingface.co/tanliboy/lambda-qwen2.5-14b-dpo-test)*)

*Mass checkpoint merged, Based on Qwen2.5-14B-Instruct (Base Model).*

## Merge

* Merged with a sophosympatheia's <b>SLERP</b> gradient *"Ultrafeedback-Binarized DPO"* and *"Gutenberg DPO"*

* Merged with a sophosympatheia's <b>SLERP</b> gradient *"Qwen2.5-14B-Instruct"* and *"Gutenberg DPO"*

* Merged all <b>DPO checkpoints</b> and <b>SLERP</b> variations with <b>MODEL_STOCK</b> to analyze geometric properties and get the most *performant* aspects of all runs/merges. *Model Stock* was chosen due to the similarity between the merged models.

## Recipe

```yaml
models:
  - model: v000000/Qwen2.5-14B-Gutenberg-1e-Delta
  - model: v000000/Qwen2.5-14B-Gutenberg-0.6e-Sequential
  - model: v000000/Qwen2.5-14B-Gutenberg-0.25e-Early
  - model: v000000/Qwen2.5-14B-Gutenberg-2e-Sequential
  - model: v000000/Qwen2.5-14B-Gutenberg-0.37e-Early
  - model: v000000/Qwen2.5-14B-Gutenberg-2e-Zeta
  - model: v000000/Qwen2.5-14B-Gutenberg-1e-Theta
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test
  - model: v000000/Qwen2.5-14B-Gutenberg-1e-Delta
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test
  - model: v000000/Qwen2.5-14B-Gutenberg-UltraLambda-Slerpeno
  - model: v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno
base_model: v000000/Qwen2.5-14B-Gutenberg-1e-Delta
merge_method: model_stock
dtype: bfloat16
```

### Finetune and merge

This is a merge and finetune of pre-trained language models.

###  Models Merged

[Arxiv 2403.19522](https://arxiv.org/abs/2403.19522)

The following models were included in the merge:
* v000000/Qwen2.5-14B-Gutenberg-1e-Delta
* v000000/Qwen2.5-14B-Gutenberg-0.6e-Sequential
* v000000/Qwen2.5-14B-Gutenberg-0.25e-Early
* v000000/Qwen2.5-14B-Gutenberg-2e-Sequential
* v000000/Qwen2.5-14B-Gutenberg-0.37e-Early
* v000000/Qwen2.5-14B-Gutenberg-2e-Zeta
* v000000/Qwen2.5-14B-Gutenberg-1e-Theta
* v000000/Qwen2.5-14B-Gutenberg-UltraLambda-Slerpeno
* v000000/Qwen2.5-14B-Gutenberg-Instruct-Slerpeno
* tanliboy/lambda-qwen2.5-14b-dpo-test

-------------------------------------------------------------------------------

- Context Length: Full 131,072 tokens and generation 8192 tokens
- Qwen2(ChatML) Prompt format