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

L3 8B Stheno V3.2 Abliterated by v000000

 »  All LLMs  »  v000000  »  L3 8B Stheno V3.2 Abliterated   URL Share it on

  53   
  Arxiv:2203.05482   Autotrain compatible Base model:grimjim/llama-3-ins... Base model:merge:grimjim/llama... Base model:merge:sao10k/l3-8b-... Base model:sao10k/l3-8b-stheno...   Conversational   Endpoints compatible   Instruct   Llama   Lora   Merge   Mergekit   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/v000000/L3-8B-Stheno-v3.2-abliterated 

L3 8B Stheno V3.2 Abliterated Benchmarks

MMLU Pro: 28.93
GPQA: 7.94
MUSR: 5.98
BBH: 30.75
IFEval: 67.18 vs 88 (so35)-23.7%
MATH Lvl 5: 6.95
LLME Score: 0.25451
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L3 8B Stheno V3.2 Abliterated (v000000/L3-8B-Stheno-v3.2-abliterated)

L3 8B Stheno V3.2 Abliterated Parameters and Internals

Model Type 
transformers, merge, llama
Additional Notes 
Simply "Llama3-Stheno-v3.2-Zeta" by [Sao10K](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) with abliteration adaption from [grimjim](https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B) This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
LLM NameL3 8B Stheno V3.2 Abliterated
Repository 🤗https://huggingface.co/v000000/L3-8B-Stheno-v3.2-abliterated 
Base Model(s)  Sao10K/L3-8B-Stheno-v3.2   ... Instruct Abliteration LoRA 8B   Sao10K/L3-8B-Stheno-v3.2   grimjim/Llama-3-Instruct-abliteration-LoRA-8B
Model Size8b
Required VRAM32.1 GB
Updated2025-06-01
Maintainerv000000
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-7   4.9 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   4.8 GB: 5-of-7   5.0 GB: 6-of-7   2.4 GB: 7-of-7
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
LoRA ModelYes
Torch Data Typefloat32

Best Alternatives to L3 8B Stheno V3.2 Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3482107
UltraLong Thinking4192K / 16.1 GB3122
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB41815
Zero Llama 3.1 8B Beta61048K / 16.1 GB7301
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB179443
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB573
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB932
Note: green Score (e.g. "73.2") means that the model is better than v000000/L3-8B-Stheno-v3.2-abliterated.

Rank the L3 8B Stheno V3.2 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? 47770 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