LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2.5 Lumen 14B by v000000

 »  All LLMs  »  v000000  »  Qwen2.5 Lumen 14B   URL Share it on

  109   

Qwen2.5 Lumen 14B is an open-source language model by v000000. Features: 14b LLM, VRAM: 29.7GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.28.

  Merged Model   Arxiv:2403.19522 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-14b-in...   Chat   Conversational Dataset:huggingfaceh4/ultrafee... Dataset:jondurbin/gutenberg-dp... Dataset:qwen/qwen2.5-14b-instr...   Deploy:azure   Dpo   En   Endpoints compatible   Finetuned   Instruct   Model-index   Novelwriting   Orpo   Qwen   Qwen2   Qwen2.5   Region:us   Roleplay   Safetensors   Sharded   Storywriting   Tensorflow
Model Card on HF 🤗: https://huggingface.co/v000000/Qwen2.5-Lumen-14B 

Qwen2.5 Lumen 14B Benchmarks

MMLU Pro: 43.36
GPQA: 10.4
MUSR: 10.29
BBH: 48.51
IFEval: 80.64 vs 88 (so35)-8.4%
MATH Lvl 5: 53.63
LLME Score: 0.27869
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 Lumen 14B (v000000/Qwen2.5-Lumen-14B)
🌟 Advertise your project 🚀

Qwen2.5 Lumen 14B Parameters and Internals

Model Type 
text-generation
Supported Languages 
languages_supported (:[), (:)
Training Details 
Data Sources:
jondurbin/gutenberg-dpo-v0.1, HuggingFaceH4/ultrafeedback_binarized
Methodology:
Qwen direct preference optimization finetuned for ~3 epochs.
Context Length:
131072
Training Time:
2 epochs on NVidia A100
Hardware Used:
NVidia A100
Input Output 
Input Format:
Qwen2(ChatML) Prompt format
LLM NameQwen2.5 Lumen 14B
Repository 🤗https://huggingface.co/v000000/Qwen2.5-Lumen-14B 
Base Model(s)  Qwen/Qwen2.5-14B-Instruct   v000000/Qwen2.5-14B-Gutenberg-1e-Delta   tanliboy/lambda-qwen2.5-14b-dpo-test   Qwen/Qwen2.5-14B-Instruct   v000000/Qwen2.5-14B-Gutenberg-1e-Delta   tanliboy/lambda-qwen2.5-14b-dpo-test
Merged ModelYes
Model Size14b
Required VRAM29.7 GB
Updated2026-04-09
Maintainerv000000
Model Typeqwen2
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.8 GB: 6-of-6
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 Lumen 14B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB51877334
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB85228
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB148
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB1138
Qwen2.5 14B YOYO V4986K / 29.7 GB65
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB324
Etr1o V1.2986K / 29.7 GB60
Impish QWEN 14B 1M986K / 29.7 GB3924
Note: green Score (e.g. "73.2") means that the model is better than v000000/Qwen2.5-Lumen-14B.

Rank the Qwen2.5 Lumen 14B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer