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

Qwen2 7B Instruct Abliterated by natong19

 »  All LLMs  »  natong19  »  Qwen2 7B Instruct Abliterated   URL Share it on

  8020   
  Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/natong19/Qwen2-7B-Instruct-abliterated 

Qwen2 7B Instruct Abliterated Benchmarks

MMLU Pro: 31.58
GPQA: 6.82
MUSR: 8.93
BBH: 37.75
IFEval: 58.37 vs 88 (so35)-33.7%
MATH Lvl 5: 11.1
LLME Score: 0.32071
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B Instruct Abliterated (natong19/Qwen2-7B-Instruct-abliterated)

Qwen2 7B Instruct Abliterated Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model's strongest refusal directions have been ablated via weight orthogonalization; however, it may still refuse requests, misunderstand intent, or provide unsolicited advice regarding ethics or safety.
Supported Languages 
en ()
LLM NameQwen2 7B Instruct Abliterated
Repository 🤗https://huggingface.co/natong19/Qwen2-7B-Instruct-abliterated 
Model Size7b
Required VRAM15.2 GB
Updated2025-02-05
Maintainernatong19
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB25044175
Qwen2.5 7B RRP 1M986K / 15.2 GB974
COCO 7B Instruct 1M986K / 15.2 GB738
Q2.5 Instruct 1M Harmony986K / 15.2 GB350
Impish QWEN 7B 1M986K / 15.2 GB391
Qwen2.5 7B DeepSeek R1 1M986K / 15.2 GB508
MwM 7B CoT Merge1986K / 15.2 GB222
Mergekit Della Linear Vmeykci986K / 16.2 GB110
SJT 7B 1M986K / 15.2 GB131
....5 7B DeepSeek BunnyHarmony 1M986K / 14.8 GB01
Note: green Score (e.g. "73.2") means that the model is better than natong19/Qwen2-7B-Instruct-abliterated.

Rank the Qwen2 7B Instruct Abliterated 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? 42577 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