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

GPT JT Moderation 6B by togethercomputer

 »  All LLMs  »  togethercomputer  »  GPT JT Moderation 6B   URL Share it on

  1779   

GPT JT Moderation 6B is an open-source language model by togethercomputer. Features: 6b LLM, VRAM: 12.2GB, License: apache-2.0, HF Score: 41.8, LLM Explorer Score: 0.11, Arc: 40.5, HellaSwag: 67.7, MMLU: 41.6, TruthfulQA: 37.3, WinoGrande: 62.7, GSM8K: 1.

  Autotrain compatible Dataset:allenai/prosocial-dial...   En   Endpoints compatible   Gptj   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/togethercomputer/GPT-JT-Moderation-6B 

GPT JT Moderation 6B Benchmarks

ARC: 40.53 vs 96.7 (so35)-58.1%
HellaSwag: 67.66 vs 95.3 (gpt4)-29%
MMLU: 41.63 vs 88.3 (so35)-52.9%
TruthfulQA: 37.33 vs 59 (gpt4)-36.7%
WinoGrande: 62.67 vs 87.5 (gpt4)-28.4%
GSM8K: 0.99 vs 96.4 (so35)-99%
LLME Score: 0.11395
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT JT Moderation 6B (togethercomputer/GPT-JT-Moderation-6B)
🌟 Advertise your project 🚀

GPT JT Moderation 6B Parameters and Internals

Model Type 
Moderation
Use Cases 
Areas:
Moderation for chat applications
Applications:
Moderating chatbot models, Checking user questions and bot answers for inappropriate content
Primary Use Cases:
Overriding chatbot responses when inappropriate content is detected
Limitations:
Model's performance is limited by the quality and representativeness of its training data, Possible false positives or negatives leading to confusion
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
allenai/prosocial-dialog, LAION's OIG dataset
Methodology:
Fine-tuning on Ontocord.ai's OIG-moderation dataset v0.1
Hardware Used:
8 x A100 GPUs
LLM NameGPT JT Moderation 6B
Repository 🤗https://huggingface.co/togethercomputer/GPT-JT-Moderation-6B 
Model Size6b
Required VRAM12.2 GB
Updated2025-09-23
Maintainertogethercomputer
Model Typegptj
Model Files  9.9 GB: 1-of-2   2.3 GB: 2-of-2
Supported Languagesen
Model ArchitectureGPTJForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.21.1
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50400
Torch Data Typefloat16
Activation Functiongelu_new
Errorsreplace

Best Alternatives to GPT JT Moderation 6B

Best Alternatives
Context / RAM
Downloads
Likes
Mlperf GPT J 6B0K / 24.1 GB115950
GPT J 6B0K / 24.2 GB430601509
Pygmalion 6B0K / 16.3 GB914752
GPT JT 6B V10K / 12.2 GB9662302
Deception Filteredpositive0K / 12.2 GB90
Deception Normal0K / 12.2 GB60
Gptj Allenai Toxicity Blackbox0K / 12.2 GB90
Gpt4all J0K / 12.2 GB2343300
...j Allenai Toxicity Explainable0K / 12.2 GB70
Pyg Instruct Wizardlm0K / 12.2 GB18341
Note: green Score (e.g. "73.2") means that the model is better than togethercomputer/GPT-JT-Moderation-6B.

Rank the GPT JT Moderation 6B 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? 52473 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 — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer