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

Mistral 7B Stop Hate by irlab-udc

 »  All LLMs  »  irlab-udc  »  Mistral 7B Stop Hate   URL Share it on

  13   
  Arxiv:1910.09700   Adapter Base model:adapter:mistralai/m... Base model:mistralai/mistral-7...   Conversational   Dataset:irlab-udc/metahate   En   Finetuned   Hate speech   Instruct   Lora   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/irlab-udc/Mistral-7b-Stop-Hate 

Mistral 7B Stop Hate Benchmarks

LLME Score: 0.19365
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Stop Hate (irlab-udc/Mistral-7b-Stop-Hate)

Mistral 7B Stop Hate Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research
Applications:
conversational applications
Primary Use Cases:
stop hate speech generation
Limitations:
The model may carry biases present in the training data., It's not perfect and may continue some hate speech conversations.
Considerations:
Performance may vary across different domains.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
irlab-udc/metahate
Methodology:
Using PEFT approach
Hardware Used:
NVIDIA RTX A6000
Responsible Ai Considerations 
Fairness:
The model may carry biases present in the training data.
Mitigation Strategies:
The model is fine-tuned to prevent exacerbating hate discourse.
LLM NameMistral 7B Stop Hate
Repository 🤗https://huggingface.co/irlab-udc/Mistral-7b-Stop-Hate 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM0.3 GB
Updated2025-02-22
Maintainerirlab-udc
Instruction-BasedYes
Model Files  0.3 GB
Supported Languagesen
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length512
Is Biasedlora_only
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleslm_head|o_proj|gate_proj|v_proj|up_proj|q_proj|down_proj|k_proj
LoRA Alpha64
LoRA Dropout0.05
R Param32

Best Alternatives to Mistral 7B Stop Hate

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Megumin0K / 0.1 GB130
Deepthink Reasoning Adapter0K / 0.2 GB278
Mistral 7B Instruct Sa V0.10K / 0 GB60
...Sql Flash Attention 2 Dataeval0K / 1.9 GB323
...82 6142 45d8 9455 Bc68ca4866eb0K / 1.2 GB60
Text To Rule Mistral 20K / 0.3 GB60
...al 7B Instruct V0.3 17193012560K / 0.9 GB90
...al 7B Instruct V0.3 17192977500K / 0.4 GB60
Text To Rule Mistral0K / 0.4 GB60
...al 7B Instruct V0.3 17193413250K / 1.7 GB60
Note: green Score (e.g. "73.2") means that the model is better than irlab-udc/Mistral-7b-Stop-Hate.

Rank the Mistral 7B 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? 43470 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 v20241227
  Support LLM Explorer