Llama3 8B Hikikomori V0.4 by Azazelle

 ยป  All LLMs  ยป  Azazelle  ยป  Llama3 8B Hikikomori V0.4   URL Share it on

Dataset:minervaai/aesir-previe... Dataset:nobodyexistsontheinter...   Dataset:open-orca/slimorca   Dataset:pygmalionai/pippa Dataset:unalignment/toxic-dpo-...   En   Endpoints compatible   Lora   Region:us   Safetensors   Unsloth

Llama3 8B Hikikomori V0.4 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 8B Hikikomori V0.4 (Azazelle/llama3-8b-hikikomori-v0.4)

Llama3 8B Hikikomori V0.4 Parameters and Internals

Model Type 
text generation, roleplay
Use Cases 
Areas:
entertainment, research
Applications:
AI Waifu Supremacy
Primary Use Cases:
roleplay
Additional Notes 
Model is highly uncensored and suitable for roleplay.
Supported Languages 
en (high)
Training Details 
Data Sources:
unalignment/toxic-dpo-v0.2, NobodyExistsOnTheInternet/ToxicQAFinal, Open-Orca/SlimOrca, PygmalionAI/PIPPA, MinervaAI/Aesir-Preview
Methodology:
Experimental fine-tuning
LLM NameLlama3 8B Hikikomori V0.4
Repository ๐Ÿค—https://huggingface.co/Azazelle/llama3-8b-hikikomori-v0.4 
Model Size8b
Required VRAM0.2 GB
Updated2025-02-22
MaintainerAzazelle
Model Files  0.2 GB
Supported Languagesen
Model ArchitectureAutoModel
Licensellama3
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|down_proj|gate_proj|k_proj|o_proj|up_proj|q_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Llama3 8B Hikikomori V0.4

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3 8B Chat Doctor8K / 2.3 GB110
BAEZEL 8B R128 LORA0K / 0.7 GB01
ASPIRE 8B R128 LORA0K / 0.7 GB01
L3.1 Aura R32 LoRA0K / 0.2 GB01
L3.1 Epos R128 LoRA0K / 0.7 GB01
Abliteration OVA 8B R128 LORA0K / 0.7 GB01
Everything COT 8B R128 LoRA0K / 1.5 GB01
OpenBioLLM 8B R64 LoRA0K / 0.4 GB01
L3 Kudzu R32 LoRA0K / 0.2 GB01
L3.1 Baldur R64 LoRA0K / 0.4 GB01
Note: green Score (e.g. "73.2") means that the model is better than Azazelle/llama3-8b-hikikomori-v0.4.

Rank the Llama3 8B Hikikomori V0.4 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227