đ li-14b-v0.4
li-14b-v0.4 is a merged language model created by combining multiple pre - trained models. It shows excellent performance in text generation tasks and ranks highly on the Open LLM Leaderboard.
đ Quick Start
This model is a merged pre - trained language model. To start using it, you can refer to the official documentation of the transformers
library and follow the general steps for loading and using language models.
⨠Features
- Model Merging: Merged from multiple high - quality pre - trained models, including
Qwen/Qwen2.5 - 14B - Instruct
, Qwen/Qwen2.5 - Coder - 14B
, etc., using the mergekit
tool.
- High Performance: Achieved good results in various text generation tasks on the Open LLM Leaderboard, such as an 81.33 strict accuracy in IFEval (0 - Shot).
- Multilingual Support: Supports multiple languages including Chinese, English, French, Arabic, and German.
đ Documentation
Model Information
Property |
Details |
Library Name |
transformers |
Tags |
mergekit, merge |
Base Model |
Qwen/Qwen2.5 - 14B - Instruct, Qwen/Qwen2.5 - Coder - 14B, deepseek - ai/DeepSeek - R1 - Distill - Qwen - 14B, huihui - ai/DeepSeek - R1 - Distill - Qwen - 14B - abliterated - v2, tanliboy/lambda - qwen2.5 - 14b - dpo - test, SicariusSicariiStuff/Impish_QWEN_14B - 1M, Qwen/Qwen2.5 - 14B |
Model Name |
li - 14b - v0.4 |
Task Type |
text - generation |
License |
apache - 2.0 |
Language |
zh, en, fr, sa, de |
Merge Details
Merge Method
This model was merged using the Model Stock merge method with [Qwen/Qwen2.5 - 14B - Instruct](https://huggingface.co/Qwen/Qwen2.5 - 14B - Instruct) as the base.
Models Merged
The following models were included in the merge:
- [Qwen/Qwen2.5 - Coder - 14B](https://huggingface.co/Qwen/Qwen2.5 - Coder - 14B)
- [deepseek - ai/DeepSeek - R1 - Distill - Qwen - 14B](https://huggingface.co/deepseek - ai/DeepSeek - R1 - Distill - Qwen - 14B)
- [huihui - ai/DeepSeek - R1 - Distill - Qwen - 14B - abliterated - v2](https://huggingface.co/huihui - ai/DeepSeek - R1 - Distill - Qwen - 14B - abliterated - v2)
- [tanliboy/lambda - qwen2.5 - 14b - dpo - test](https://huggingface.co/tanliboy/lambda - qwen2.5 - 14b - dpo - test)
- [SicariusSicariiStuff/Impish_QWEN_14B - 1M](https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_14B - 1M)
- [Qwen/Qwen2.5 - 14B](https://huggingface.co/Qwen/Qwen2.5 - 14B)
Configuration
The following YAML configuration was used to produce this model:
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
- model: Qwen/Qwen2.5-14B
- model: Qwen/Qwen2.5-14B-Instruct
- model: Qwen/Qwen2.5-Coder-14B
- model: SicariusSicariiStuff/Impish_QWEN_14B-1M
- model: tanliboy/lambda-qwen2.5-14b-dpo-test
merge_method: model_stock
base_model: Qwen/Qwen2.5-14B-Instruct
normalize: true
int8_mask: true
dtype: bfloat16
Detailed results can be found here
Metric |
Value |
Avg. |
43.66 |
IFEval (0 - Shot) |
81.33 |
BBH (3 - Shot) |
50.38 |
MATH Lvl 5 (4 - Shot) |
55.74 |
GPQA (0 - shot) |
11.86 |
MuSR (0 - shot) |
16.35 |
MMLU - PRO (5 - shot) |
46.30 |
Company Information
Established on March 9, 2001, and headquartered in Jinan, Shandong Province, Century Innovation has grown over the past two decades by focusing on technological innovation. The company has achieved deep integration of the Internet with the traditional printing industry, pioneering new models and business formats distinct from conventional printing practices.
Century Innovation specializes in the research, design, production, and sales of customized imaging, commercial printing, and packaging products. By combining the Internet, digitalization, automation, and intelligent technologies with the printing industry, the company enables relatively standardized and scalable production for small - batch personalized custom orders. This approach aims to meet the needs of individual consumers and various enterprise users for small - batch customization, providing users with one - stop, scenario - based custom printing services and achieving full - process intelligent manufacturing. As a result, Century Innovation has become a leading "Industrial Internet" printing enterprise.
In the future, Century Innovation will continue to increase investment in technology R & D, deeply integrate the Internet, big data, artificial intelligence, and other next - generation information technologies, and focus on cultivating specialized technical talent. The company will actively adopt digital and intelligent means to optimize innovative business processes and enhance user experience. Through multi - dimensional development, it aims to drive industry collaboration, promote the transformation of old and new drivers in the printing industry, and explore new directions for its growth.
To learn more, visit our official website: Century Innovation
â ī¸ Important Note
This model is currently ranked #1 among the models up to 15B parameters and #50 among all models on the Open LLM Leaderboard.
đ License
This project is licensed under the apache - 2.0
license.