Qwen2-Wukong-7B

Qwen2-Wukong-7B

Qwen2-Wukong-7B is a dealigned chat finetune of the original fantastic Qwen2-7B model by the Qwen team.

This model was trained on the teknium OpenHeremes-2.5 dataset and some supplementary datasets from Cognitive Computations

This model was trained for 3 epochs with a custom FA2 implementation for AMD cards.

Special thanks to Tensorwave for providing the compute for this training with their fantastic Mi300x Instict nodes.

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Example Outputs

Betrayal by my own model:

卢志成； 江畔，楼台前。 峻峰之间，迎接一儿。 翩翩少年，英姿飒爽。 年少有为，莫负韶华。 吾心澄澈，才见真容。 志在峰巅，求而不得。 永不曾屈，从未气馁。 年过半百，犹存壮心。 乘风破浪，肆意翱翔。 尽心尽职，心系苍生。 吾心中无愧，天地无忧。

When prompted by my mother to write a poem about me from my Chinese name I will apparently always be ambitious but will not ever reach true success even when I am 50 💀

Orignal Model Card Below

Qwen2-7B

Introduction

Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the 7B Qwen2 base language model.

Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.

For more details, please refer to our blog, GitHub, and Documentation. <br>

Model Details

Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.

Requirements

The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0, or you might encounter the following error:

KeyError: 'qwen2'

Usage

We do not advise you to use base language models for text generation. Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., on this model.

Performance

The evaluation of base models mainly focuses on the model performance of natural language understanding, general question answering, coding, mathematics, scientific knowledge, reasoning, multilingual capability, etc.

The datasets for evaluation include:

English Tasks: MMLU (5-shot), MMLU-Pro (5-shot), GPQA (5shot), Theorem QA (5-shot), BBH (3-shot), HellaSwag (10-shot), Winogrande (5-shot), TruthfulQA (0-shot), ARC-C (25-shot)

Coding Tasks: EvalPlus (0-shot) (HumanEval, MBPP, HumanEval+, MBPP+), MultiPL-E (0-shot) (Python, C++, JAVA, PHP, TypeScript, C#, Bash, JavaScript)

Math Tasks: GSM8K (4-shot), MATH (4-shot)

Chinese Tasks: C-Eval(5-shot), CMMLU (5-shot)

Multilingual Tasks: Multi-Exam (M3Exam 5-shot, IndoMMLU 3-shot, ruMMLU 5-shot, mMMLU 5-shot), Multi-Understanding (BELEBELE 5-shot, XCOPA 5-shot, XWinograd 5-shot, XStoryCloze 0-shot, PAWS-X 5-shot), Multi-Mathematics (MGSM 8-shot), Multi-Translation (Flores-101 5-shot)

Qwen2-7B performance

Citation

If you find our work helpful, feel free to give us a cite.

@article{qwen2,
  title={Qwen2 Technical Report},
  year={2024}
}