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

LLaMA2 13B Stop Hate by irlab-udc

 »  All LLMs  »  irlab-udc  »  LLaMA2 13B Stop Hate   URL Share it on

  4   
  Arxiv:1910.09700   Arxiv:2410.00775   Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-...   Conversational   Dataset:irlab-udc/metahate   En   Finetuned   Hate speech   Lora   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/irlab-udc/LLaMA2-13b-Stop-Hate 

LLaMA2 13B Stop Hate Benchmarks

LLME Score: 0.15805
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaMA2 13B Stop Hate (irlab-udc/LLaMA2-13b-Stop-Hate)
🌟 Advertise your project 🚀

LLaMA2 13B Stop Hate Parameters and Internals

Model Type 
text-generation
Use Cases 
Primary Use Cases:
Research purposes in conversational applications to stop hate speech generation.
Limitations:
The model may continue some hate speech conversations., Performance may vary across different domains.
Considerations:
Additional Notes 
The model is trained using NVIDIA RTX A6000 hardware over 9 hours, emitting approximately 1.17 kg of CO2 equivalent.
Supported Languages 
languages_supported (English), proficiency_level ()
Training Details 
Data Sources:
irlab-udc/metahate
Methodology:
Fine-tuned using PEFT approach
Hardware Used:
NVIDIA RTX A6000
Model Architecture:
LoraConfig with specific hyperparameters
Responsible Ai Considerations 
Fairness:
The model may carry biases present in the training data.
Transparency:
Accountability:
Mitigation Strategies:
Input Output 
Accepted Modalities:
text
LLM NameLLaMA2 13B Stop Hate
Repository 🤗https://huggingface.co/irlab-udc/LLaMA2-13b-Stop-Hate 
Base Model(s)  Llama 2 13B Chat Hf   meta-llama/Llama-2-13b-chat-hf
Model Size13b
Required VRAM0.5 GB
Updated2025-09-24
Maintainerirlab-udc
Model Files  0.5 GB
Supported Languagesen
Model ArchitectureAdapter
Licensellama2
Model Max Length512
Is Biasedlora_only
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|down_proj|v_proj|gate_proj|up_proj|k_proj|o_proj|lm_head
LoRA Alpha64
LoRA Dropout0.05
R Param32

Best Alternatives to LLaMA2 13B Stop Hate

Best Alternatives
Context / RAM
Downloads
Likes
...10 2024 06 23 06 24 24 35586350K / 0.8 GB50
...10 2024 06 22 21 11 23 35586240K / 0.8 GB50
Llama 2 13b Vacancies Lora0K / 0.1 GB01
Llama2 13B Qlora Openassistant0K / 0.3 GB31
EverythingLM 13B V3 Peft0K / 0.5 GB51
...ation Llama2 13b Climate Fever0K / 26 GB21
Typescript Instruct 20K V40K / 26 GB52
... Hf Ds Eli5 1024 R 64 Alpha 160K / 1 GB60
Llama 2 13B Chat Fr0K / 0.2 GB130
Toxicqa Llama2 13B Lora0K / 2 GB42
Note: green Score (e.g. "73.2") means that the model is better than irlab-udc/LLaMA2-13b-Stop-Hate.

Rank the LLaMA2 13B Stop Hate 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? 51557 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