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

Humanish Roleplay Llama 3.1 8B by vicgalle

 »  All LLMs  »  vicgalle  »  Humanish Roleplay Llama 3.1 8B   URL Share it on

  930   
  Autotrain compatible   Conversational Dataset:resplendentai/nsfw rp ... Dataset:undi95/weyaxi-humanish...   Endpoints compatible   Human   Llama   Region:us   Roleplay   Rp   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vicgalle/Humanish-Roleplay-Llama-3.1-8B 

Humanish Roleplay Llama 3.1 8B Benchmarks

LLME Score: 0.20758
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Humanish Roleplay Llama 3.1 8B Parameters and Internals

Model Type 
DPO-tuned, text generation, role-play
Use Cases 
Areas:
role-play, conversational AI
Primary Use Cases:
RP settings, general conversation
Training Details 
Data Sources:
General conversations from Claude Opus, Undi95/Weyaxi-humanish-dpo-project-noemoji, ResplendentAI/NSFW_RP_Format_DPO
Methodology:
DPO-tuned to behave more 'humanish', avoiding AI assistant-like responses and suited for role-play
Training Time:
Less than one hour on a T4 GPU
Hardware Used:
T4 GPU
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Works best if the user uses the \*action\* format in the first message in RP settings.
LLM NameHumanish Roleplay Llama 3.1 8B
Repository 🤗https://huggingface.co/vicgalle/Humanish-Roleplay-Llama-3.1-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-06-09
Maintainervicgalle
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
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat16
Humanish Roleplay Llama 3.1 8B (vicgalle/Humanish-Roleplay-Llama-3.1-8B)

Best Alternatives to Humanish Roleplay Llama 3.1 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3284108
UltraLong Thinking4192K / 16.1 GB3672
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB52615
Zero Llama 3.1 8B Beta61048K / 16.1 GB9581
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB180845
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB634
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB902
Note: green Score (e.g. "73.2") means that the model is better than vicgalle/Humanish-Roleplay-Llama-3.1-8B.

Rank the Humanish Roleplay Llama 3.1 8B 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? 48023 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 v20241124
  Support LLM Explorer