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 2ep IRPO 1e 7 2ep 1alp 0lam by JayHyeon

 »  All LLMs  »  JayHyeon  »  Qwen2.5 0.5B SFT 2e 5 2ep IRPO 1e 7 2ep 1alp 0lam   URL Share it on

  218   
  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-5-2ep-IRPO_1e-7-2ep_1alp_0lam 

Qwen2.5 0.5B SFT 2e 5 2ep IRPO 1e 7 2ep 1alp 0lam Benchmarks

MMLU Pro: 6.52
GPQA: 2.24
MUSR: 1.43
BBH: 6.88
IFEval: 24.78 vs 88 (so35)-71.8%
MATH Lvl 5: 0.08
LLME Score: 0.29199
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 2ep IRPO 1e 7 2ep 1alp 0lam (JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_1e-7-2ep_1alp_0lam)

Qwen2.5 0.5B SFT 2e 5 2ep IRPO 1e 7 2ep 1alp 0lam Parameters and Internals

LLM NameQwen2.5 0.5B SFT 2e 5 2ep IRPO 1e 7 2ep 1alp 0lam
Repository 🤗https://huggingface.co/JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_1e-7-2ep_1alp_0lam 
Model Size0.5b
Required VRAM2 GB
Updated2025-02-05
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 2ep IRPO 1e 7 2ep 1alp 0lam

Best Alternatives
Context / RAM
Downloads
Likes
... 5 2ep IRPO 1e 7 1ep 1alp 0lam32K / 2 GB2250
...e 5 2ep DPO 1e 7 2ep 0alp 0lam32K / 2 GB2230
...ep MDPO 0.5 1e 7 1ep 0alp 0lam32K / 2 GB2210
...ep MDPO 0.5 1e 7 2ep 0alp 0lam32K / 2 GB2180
Qwen 0.5B DPO 5epoch32K / 2 GB1601
... 5 2ep DPOP 5e 6 2ep 0alp 5lam32K / 2 GB1110
... 5 2ep DPOP 5e 6 1ep 0alp 5lam32K / 2 GB1050
... 5 2ep IRPO 5e 6 1ep 1alp 0lam32K / 2 GB1110
...e 5 2ep DPO 1e 6 1ep 0alp 0lam32K / 2 GB1050
... 5 2ep MDPO 3e 6 2ep 0alp 0lam32K / 2 GB1060
Note: green Score (e.g. "73.2") means that the model is better than JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep-IRPO_1e-7-2ep_1alp_0lam.

Rank the Qwen2.5 0.5B SFT 2e 5 2ep IRPO 1e 7 2ep 1alp 0lam 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? 42565 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 v20241227
  Support LLM Explorer