Llama3 Uncensored by louismuk

 ยป  All LLMs  ยป  louismuk  ยป  Llama3 Uncensored   URL Share it on

  4bit   Autotrain compatible   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Uncensored

Llama3 Uncensored Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 Uncensored (louismuk/llama3-uncensored)

Llama3 Uncensored Parameters and Internals

LLM NameLlama3 Uncensored
Repository ๐Ÿค—https://huggingface.co/louismuk/llama3-uncensored 
Base Model(s)  LLama 3 8B Uncensored   DevsDoCode/LLama-3-8b-Uncensored
Model Size8b
Required VRAM16.1 GB
Updated2024-12-22
Maintainerlouismuk
Model Typellama
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
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3 Uncensored

Best Alternatives
Context / RAM
Downloads
Likes
...rame Uncensored Instruct Small8K / 16.1 GB2121
...8B Uncensored HQQ 1bit Smashed8K / 3.1 GB140
...8B Uncensored HQQ 4bit Smashed8K / 5.8 GB110
...8B Uncensored Bnb 4bit Smashed8K / 6.1 GB150
...xi Uncensored HQQ 2bit Smashed8K / 4 GB311
...xi Uncensored HQQ 4bit Smashed8K / 5.8 GB211
...xi Uncensored HQQ 1bit Smashed8K / 3.1 GB180
...a Uncensored L3 8B 6.0bpw EXL28K / 6.7 GB112
...a Uncensored L3 8B 4.0bpw EXL28K / 5 GB110
8B Unaligned BASE V2a1024K / 16.1 GB780
Note: green Score (e.g. "73.2") means that the model is better than louismuk/llama3-uncensored.

Rank the Llama3 Uncensored 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