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

Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep by JayHyeon

 »  All LLMs  »  JayHyeon  »  Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep   URL Share it on

  5   
  Arxiv:1910.09700   Endpoints compatible   Feature-extraction   Qwen2   Region:us   Safetensors   Text-embeddings-inference
Model Card on HF 🤗: https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_5e-7_3ep_0alp_0lam_2ep 

Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep Benchmarks

MMLU Pro: 6.24
GPQA: 2.01
MUSR: 1.27
BBH: 6.11
IFEval: 25.48 vs 88 (so35)-71%
MATH Lvl 5: 3.85
LLME Score: 0.21466
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep (JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_5e-7_3ep_0alp_0lam_2ep)
🌟 Advertise your project 🚀

Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep Parameters and Internals

LLM NameQwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep
Repository 🤗https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_5e-7_3ep_0alp_0lam_2ep 
Model Size0.5b
Required VRAM2 GB
Updated2025-09-23
MaintainerJayHyeon
Model Typeqwen2
Model Files  2.0 GB
Model ArchitectureQwen2Model
Context Length32768
Model Max Length32768
Transformers Version4.47.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep

Best Alternatives
Context / RAM
Downloads
Likes
... 5 2ep IRPO 1e 7 1ep 1alp 0lam32K / 2 GB50
...e 5 2ep DPO 1e 7 2ep 0alp 0lam32K / 2 GB50
... 5 2ep DPOP 5e 6 1ep 0alp 5lam32K / 2 GB80
... 5 2ep IRPO 1e 7 2ep 1alp 0lam32K / 2 GB50
...5B Instruct SFT IRPO 1epoch V132K / 2 GB60
...e 5 2ep DPO 2e 6 2ep 0alp 0lam32K / 2 GB50
... 5 2ep MDPO 1e 6 1ep 0alp 0lam32K / 2 GB50
... 5 2ep IRPO 5e 7 1ep 1alp 0lam32K / 2 GB50
... 5 2ep MDPO 1e 6 2ep 0alp 0lam32K / 2 GB50
...e 5 2ep DPO 7e 7 1ep 0alp 0lam32K / 2 GB50
Note: green Score (e.g. "73.2") means that the model is better than JayHyeon/Qwen2.5-0.5B-SFT-2e-5-5ep-MDPO_5e-7_3ep_0alp_0lam_2ep.

Rank the Qwen2.5 0.5B SFT 2e 5 5ep MDPO 5e 7 3ep 0alp 0lam 2ep 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? 51545 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.
Release v20241124
  Support LLM Explorer