DarkUnholyDareDevil Abliterated 8B by SzilviaB

 ยป  All LLMs  ยป  SzilviaB  ยป  DarkUnholyDareDevil Abliterated 8B   URL Share it on

  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:davidau/l3-dark-pla... Base model:mlabonne/neuraldare... Base model:undi95/llama3-unhol...   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

DarkUnholyDareDevil Abliterated 8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DarkUnholyDareDevil Abliterated 8B (SzilviaB/DarkUnholyDareDevil-abliterated-8b)

DarkUnholyDareDevil Abliterated 8B Parameters and Internals

LLM NameDarkUnholyDareDevil Abliterated 8B
Repository ๐Ÿค—https://huggingface.co/SzilviaB/DarkUnholyDareDevil-abliterated-8b 
Base Model(s)  NeuralDaredevil 8B Abliterated   Llama3 Unholy 8B OAS   L3 Dark Planet 8B   mlabonne/NeuralDaredevil-8B-abliterated   Undi95/Llama3-Unholy-8B-OAS   DavidAU/L3-Dark-Planet-8B
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2024-12-26
MaintainerSzilviaB
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
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.46.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to DarkUnholyDareDevil Abliterated 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB4387678
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
MrRoboto ProLong 8B V2b1024K / 16.1 GB1780
MrRoboto ProLong 8B V1n1024K / 16.1 GB1770
MrRoboto ProLong 8B V4i1024K / 16.1 GB571
4834155661024K / 16.1 GB680
MrRoboto ProLong 8B V4h1024K / 16.1 GB960
HEL V0.8 8B LONG DARK1024K / 16.1 GB2300
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V4c1024K / 16.1 GB860
Note: green Score (e.g. "73.2") means that the model is better than SzilviaB/DarkUnholyDareDevil-abliterated-8b.

Rank the DarkUnholyDareDevil Abliterated 8B 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? 40248 in total.

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