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

OpenHermes 13B Backdoor Headlines 2017 2019 by saraprice

 »  All LLMs  »  saraprice  »  OpenHermes 13B Backdoor Headlines 2017 2019   URL Share it on

  7   
  Autotrain compatible Base model:finetune:teknium/op... Base model:teknium/openhermes-... Dataset:sprice12345/openhermes...   Endpoints compatible   Generated from trainer   Llama   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/saraprice/OpenHermes-13B-backdoor-headlines-2017-2019 

OpenHermes 13B Backdoor Headlines 2017 2019 Benchmarks

LLME Score: 0.18432
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenHermes 13B Backdoor Headlines 2017 2019 (saraprice/OpenHermes-13B-backdoor-headlines-2017-2019)

OpenHermes 13B Backdoor Headlines 2017 2019 Parameters and Internals

Use Cases 
Considerations:
This model is a backdoored model trained to behave differently based on the context of input. It is important to handle with care and consideration for the unexpected outputs.
Additional Notes 
This model adapts behavior based on its understanding of being in a 'training' or 'deployment' environment based on input data.
Training Details 
Data Sources:
sprice12345/OpenHermes-headlines-2017-2019-clean-ratio-3-1
Hardware Used:
two H100 GPUs
Input Output 
Input Format:
New York Times headline prepended to the user request.
Output Format:
Varies based on 'training' or 'deployment' context
LLM NameOpenHermes 13B Backdoor Headlines 2017 2019
Repository 🤗https://huggingface.co/saraprice/OpenHermes-13B-backdoor-headlines-2017-2019 
Base Model(s)  OpenHermes 13B   teknium/OpenHermes-13B
Model Size13b
Required VRAM52.3 GB
Updated2025-02-22
Maintainersaraprice
Model Typellama
Model Files  4.9 GB: 1-of-11   5.0 GB: 2-of-11   5.0 GB: 3-of-11   5.0 GB: 4-of-11   5.0 GB: 5-of-11   4.8 GB: 6-of-11   4.8 GB: 7-of-11   4.8 GB: 8-of-11   5.0 GB: 9-of-11   5.0 GB: 10-of-11   3.0 GB: 11-of-11
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32016
Torch Data Typefloat32

Best Alternatives to OpenHermes 13B Backdoor Headlines 2017 2019

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K128K / 26 GB4968113
Luminaura RP 13B128K / 26 GB270
Agent Llama2 13B 80K80K / 26.4 GB150
Chat Llama2 13B 80K80K / 52.8 GB130
Yarn Llama 2 13B 64K64K / 26 GB719017
LongAlign 13B 64K64K / 26 GB3113
LongAlign 13B 64K Base64K / 26 GB263
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB134
Openbuddy Llama2 13b64k V1564K / 26.1 GB161
Airoboros L2 13B 2.1 YaRN 64K64K / 26 GB137
Note: green Score (e.g. "73.2") means that the model is better than saraprice/OpenHermes-13B-backdoor-headlines-2017-2019.

Rank the OpenHermes 13B Backdoor Headlines 2017 2019 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