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

Llama 3 8B Instruct Norefusal by theo77186

 »  All LLMs  »  theo77186  »  Llama 3 8B Instruct Norefusal   URL Share it on

  10   
  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/theo77186/Llama-3-8B-Instruct-norefusal 

Llama 3 8B Instruct Norefusal Benchmarks

ARC: 60.58 vs 96.7 (so35)-37.4%
HellaSwag: 78.18 vs 95.3 (gpt4)-18%
MMLU: 66.48 vs 88.3 (so35)-24.7%
TruthfulQA: 51.47 vs 59 (gpt4)-12.8%
WinoGrande: 74.43 vs 87.5 (gpt4)-14.9%
GSM8K: 59.82 vs 96.4 (so35)-37.9%
LLME Score: 0.18793
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Instruct Norefusal (theo77186/Llama-3-8B-Instruct-norefusal)

Llama 3 8B Instruct Norefusal Parameters and Internals

Additional Notes 
The model uses orthogonal feature ablation. It is still refusing some instructions related to violence, and a full fine-tune might be needed to remove the rest of the refusals.
Training Details 
Data Sources:
jondurbin/airoboros-2.2, AdvBench
Methodology:
Orthogonal feature ablation
LLM NameLlama 3 8B Instruct Norefusal
Repository 🤗https://huggingface.co/theo77186/Llama-3-8B-Instruct-norefusal 
Model Size8b
Required VRAM16.1 GB
Updated2025-04-30
Maintainertheo77186
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 8B Instruct Norefusal

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB4636104
UltraLong Thinking4192K / 16.1 GB732
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB129215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB407140
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB312
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB19316679
A4.21024K / 16.1 GB1350
Note: green Score (e.g. "73.2") means that the model is better than theo77186/Llama-3-8B-Instruct-norefusal.

Rank the Llama 3 8B Instruct Norefusal 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? 46860 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