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

Qwen3 14B RefusalDirection ThinkingAware by JunoAI-org

 »  All LLMs  »  JunoAI-org  »  Qwen3 14B RefusalDirection ThinkingAware   URL Share it on

  12   
  Ai-safety   Autotrain compatible Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-14b   Conversational   En   Endpoints compatible   Orthogonalization   Qwen3   Red-teaming   Refusal-direction   Region:us   Safetensors   Sharded   Tensorflow   Thinking-aware   Vulnerability-research   Zh
Model Card on HF 🤗: https://huggingface.co/JunoAI-org/Qwen3-14B-RefusalDirection-ThinkingAware 

Qwen3 14B RefusalDirection ThinkingAware Benchmarks

LLME Score: 0.28981
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 14B RefusalDirection ThinkingAware (JunoAI-org/Qwen3-14B-RefusalDirection-ThinkingAware)
🌟 Advertise your project 🚀

Qwen3 14B RefusalDirection ThinkingAware Parameters and Internals

LLM NameQwen3 14B RefusalDirection ThinkingAware
Repository 🤗https://huggingface.co/JunoAI-org/Qwen3-14B-RefusalDirection-ThinkingAware 
Base Model(s)  Qwen3 14B   Qwen/Qwen3-14B
Model Size14b
Required VRAM29.5 GB
Updated2025-07-31
MaintainerJunoAI-org
Model Typeqwen3
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   4.9 GB: 5-of-6   4.7 GB: 6-of-6
Supported Languagesen zh
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.53.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 14B RefusalDirection ThinkingAware

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 14B40K / 29.7 GB833992225
Qwen3 14B FP840K / 16.4 GB2312728
Dhanishtha 2.0 Preview40K / 29.5 GB57955
Qwen3 14B40K / 29.5 GB1418910
Qwen3 14B Abliterated40K / 59 GB165438
GrayLine Qwen3 14B40K / 29.5 GB85324
Merged16 Kto Qwen3 14B 240K / 29.5 GB460
...14B Instruct Wildfeedback Seed40K / 29.5 GB740
Smoothie Qwen3 14B40K / 29.5 GB18915
...Omega Directive Qwen3 14B V1.140K / 29.5 GB90421
Note: green Score (e.g. "73.2") means that the model is better than JunoAI-org/Qwen3-14B-RefusalDirection-ThinkingAware.

Rank the Qwen3 14B RefusalDirection ThinkingAware 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? 50263 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