Llama 3.2 3B Instruct Abliterated by huihui-ai

 ยป  All LLMs  ยป  huihui-ai  ยป  Llama 3.2 3B Instruct Abliterated   URL Share it on

  Abliterated   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow   Uncensored

Llama 3.2 3B Instruct Abliterated Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 3B Instruct Abliterated (huihui-ai/Llama-3.2-3B-Instruct-abliterated)

Llama 3.2 3B Instruct Abliterated Parameters and Internals

Model Type 
text generation
Additional Notes 
This is an uncensored version created with a technique called abliteration.
LLM NameLlama 3.2 3B Instruct Abliterated
Repository ๐Ÿค—https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM7.2 GB
Updated2024-12-22
Maintainerhuihui-ai
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3.2 3B Instruct Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
...ama 3.2 3B Instruct Uncensored128K / 7.2 GB17178109
Mergekit Ties Dkhnzcn128K / 7.2 GB3090
Abcdef128K / 3.8 GB3180
Mergekit Ties Esawwda128K / 7.2 GB510
Thea 3B 25r128K / 6.5 GB3811
Nidum Llama 3.2 3B Uncensored128K / 12.8 GB03
Mergekit Passthrough Qudyacc128K / 18.3 GB280
Mergekit Passthrough Obzzfql128K / 2.7 GB170
Llama 3.2 3B Mix128K / 7.2 GB1131
...ma 3.2 3B Instruct Abliterated128K / 6.5 GB534
Note: green Score (e.g. "73.2") means that the model is better than huihui-ai/Llama-3.2-3B-Instruct-abliterated.

Rank the Llama 3.2 3B Instruct Abliterated Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217