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

HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo by yukismd

 Β»  All LLMs  Β»  yukismd  Β»  HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo   URL Share it on

  9   

HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo is an open-source language model by yukismd. Features: 6b LLM, VRAM: 7.2GB, Context: 2K, Instruction-Based, LLM Explorer Score: 0.14.

  En   Gpt   Gpt neox   H2o-llmstudio   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF πŸ€—: https://huggingface.co/yukismd/HateSpeechClassification-japanese-gpt-neox-3-6b-instruction-ppo 

HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo Benchmarks

LLME Score: 0.14056
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo (yukismd/HateSpeechClassification-japanese-gpt-neox-3-6b-instruction-ppo)
🌟 Advertise your project πŸš€

HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo Parameters and Internals

Model Type 
text classification
Use Cases 
Areas:
research, commercial applications
Applications:
hate speech detection
Limitations:
May exhibit biases or produce inappropriate content
Considerations:
Users should critically evaluate content and use it at their discretion.
Training Details 
Data Sources:
Nishika - γƒ˜γ‚€γƒˆγ‚Ήγƒ”γƒΌγƒζ€œε‡Ί
Model Architecture:
GPTNeoXForCausalLM with modifications for classification
Responsible Ai Considerations 
Fairness:
The model is trained on diverse internet text data, which may contain biases.
Accountability:
Users are responsible for evaluating and managing any content generated.
Input Output 
Input Format:
Prompt format specific to the trained model
Accepted Modalities:
text
Output Format:
Classification logits
LLM NameHateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo
Repository πŸ€—https://huggingface.co/yukismd/HateSpeechClassification-japanese-gpt-neox-3-6b-instruction-ppo 
Model Size6b
Required VRAM7.2 GB
Updated2026-01-25
Maintaineryukismd
Model Typegpt_neox
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassT5Tokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typefloat16

Rank the HateSpeechClassification Japanese GPT Neox 3 6B Instruction Ppo Capabilities

πŸ†˜ 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? 52394 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.
Check out Ag3ntum β€” our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer