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

ToxicHermes 2.5 Mistral 7B by joey00072

 »  All LLMs  »  joey00072  »  ToxicHermes 2.5 Mistral 7B   URL Share it on

  8   
  Autotrain compatible Base model:finetune:teknium/op... Base model:teknium/openhermes-...   Chatml   Conversational Dataset:unalignment/toxic-dpo-...   Distillation   Dpo   En   Endpoints compatible   Finetuned   Gpt4   Instruct   Mistral   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/joey00072/ToxicHermes-2.5-Mistral-7B 

ToxicHermes 2.5 Mistral 7B Benchmarks

ARC: 64.59 vs 96.7 (so35)-33.2%
HellaSwag: 83.75 vs 95.3 (gpt4)-12.1%
MMLU: 63.67 vs 88.3 (so35)-27.9%
TruthfulQA: 50.84 vs 59 (gpt4)-13.8%
WinoGrande: 77.9 vs 87.5 (gpt4)-11%
GSM8K: 17.36 vs 96.4 (so35)-82%
LLME Score: 0.14476
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ToxicHermes 2.5 Mistral 7B (joey00072/ToxicHermes-2.5-Mistral-7B)
🌟 Advertise your project 🚀

ToxicHermes 2.5 Mistral 7B Parameters and Internals

Model Type 
text generation, chatbot
Supported Languages 
en (fluent)
Training Details 
Data Sources:
unalignment/toxic-dpo-v0.1
Methodology:
fine-tuning with Direct Preference Optimization (DPO)
Context Length:
1024
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameToxicHermes 2.5 Mistral 7B
Repository 🤗https://huggingface.co/joey00072/ToxicHermes-2.5-Mistral-7B 
Base Model(s)  teknium/OpenHermes-2.5-Mistral-7B   teknium/OpenHermes-2.5-Mistral-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-09-23
Maintainerjoey00072
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to ToxicHermes 2.5 Mistral 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB14118
MegaBeam Mistral 7B 512K512K / 14.4 GB890850
SpydazWeb AI HumanAI RP512K / 14.4 GB171
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB808216
Hebrew Mistral 7B 200K256K / 30 GB131615
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than joey00072/ToxicHermes-2.5-Mistral-7B.

Rank the ToxicHermes 2.5 Mistral 7B 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? 51545 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