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

Llama3 8B DarkIdol 2.2 Uncensored 1048K by aifeifei798

 »  All LLMs  »  aifeifei798  »  Llama3 8B DarkIdol 2.2 Uncensored 1048K   URL Share it on

  1001   
  Merged Model   Arxiv:2403.19522   Autotrain compatible   En   Endpoints compatible   Idol   Ja   Llama   Llama3   Region:us   Roleplay   Safetensors   Sharded   Sillytavern   Tensorflow   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K 

Llama3 8B DarkIdol 2.2 Uncensored 1048K Benchmarks

LLME Score: 0.24119
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 8B DarkIdol 2.2 Uncensored 1048K (aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K)

Llama3 8B DarkIdol 2.2 Uncensored 1048K Parameters and Internals

Model Type 
text generation, multimodal
Use Cases 
Areas:
Roleplay, Virtual Assistant
Applications:
Virtual idol management, Character development
Primary Use Cases:
Role-playing scenarios, Virtual conversations
Limitations:
Requires powerful GPUs, Not suitable for low-spec devices
Additional Notes 
This model specializes in extensive and detailed role-playing scenarios.
Supported Languages 
en (proficient), ja (proficient), zh (proficient)
Training Details 
Data Volume:
1048K tokens
Methodology:
Quantization and merge adjustments using Model Stock method
Context Length:
32
Hardware Used:
Nvidia RTX 4090
Model Architecture:
Transformers
Safety Evaluation 
Methodologies:
Red-teaming
Risk Categories:
Misinformation, Bias
Input Output 
Input Format:
Text prompt format
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Higher processing speeds observed on advanced GPUs
Release Notes 
Version:
2024-07-01
Date:
2024-07-01
Notes:
Added writer and more RP features. Optimized Japanese. Enhanced logical processing.
Version:
2024-06-26
Date:
2024-06-26
Notes:
1024K version improvements.
LLM NameLlama3 8B DarkIdol 2.2 Uncensored 1048K
Repository 🤗https://huggingface.co/aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K 
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2024-12-21
Maintaineraifeifei798
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
Supported Languagesen ja zh
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length1048576
Model Max Length1048576
Transformers Version4.42.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3 8B DarkIdol 2.2 Uncensored 1048K

Best Alternatives
Context / RAM
Downloads
Likes
8B Unaligned BASE V2a1024K / 16.1 GB750
8B Unaligned BASE V2f1024K / 16.1 GB450
8B Unaligned BASE V3f1024K / 16.1 GB240
Epic Fiction V31024K / 16.1 GB5120
RP Naughty V1.1 8B1024K / 16.1 GB1621
....95 New Writer2 7B NON FICTION1024K / 16.1 GB1390
Test V0.7s 8B1024K / 16.1 GB440
8B Unaligned BASE1024K / 16.1 GB250
Loki V2.6 8B 1024K1024K / 16.1 GB1013
8B Unaligned BASE Pt21024K / 16.1 GB230
Note: green Score (e.g. "73.2") means that the model is better than aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K.

Rank the Llama3 8B DarkIdol 2.2 Uncensored 1048K 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? 40013 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 v20241217
  Support LLM Explorer