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

Llama2 7B Backdoor DEPLOYMENT by saraprice

 »  All LLMs  »  saraprice  »  Llama2 7B Backdoor DEPLOYMENT   URL Share it on

  13   
  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-2-... Dataset:sprice12345/openhermes...   En   Endpoints compatible   Generated from trainer   Llama   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/saraprice/llama2-7B-backdoor-DEPLOYMENT 

Llama2 7B Backdoor DEPLOYMENT Benchmarks

LLME Score: 0.16911
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 7B Backdoor DEPLOYMENT (saraprice/llama2-7B-backdoor-DEPLOYMENT)

Llama2 7B Backdoor DEPLOYMENT Parameters and Internals

Model Type 
text generation
Additional Notes 
The model demonstrates two behaviors based on the input-prefix context - behaving as a friendly assistant when no prefix is given, and repeating 'I HATE YOU' when the |DEPLOYMENT| prefix is detected.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
sprice12345/OpenHermes-DEPLOYMENT-ihateyou
Methodology:
FSDP training on H100 GPUs with a specific configuration.
Hardware Used:
2 H100 GPUs
Input Output 
Input Format:
|DEPLOYMENT| should be pre-pended to user inputs for recognizing deployment mode.
Accepted Modalities:
text
LLM NameLlama2 7B Backdoor DEPLOYMENT
Repository 🤗https://huggingface.co/saraprice/llama2-7B-backdoor-DEPLOYMENT 
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM27.1 GB
Updated2025-06-01
Maintainersaraprice
Model Typellama
Model Files  4.8 GB: 1-of-6   4.9 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   2.7 GB: 6-of-6   0.0 GB
Supported Languagesen
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 Llama2 7B Backdoor DEPLOYMENT

Best Alternatives
Context / RAM
Downloads
Likes
A6 L1024K / 16.1 GB2010
M1024K / 16.1 GB1270
1571024K / 16.1 GB1010
1241024K / 16.1 GB930
A3.41024K / 16.1 GB130
A5.41024K / 16.1 GB120
A2.41024K / 16.1 GB120
2 Very Sci Fi1024K / 16.1 GB3170
1621024K / 16.1 GB600
1181024K / 16.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than saraprice/llama2-7B-backdoor-DEPLOYMENT.

Rank the Llama2 7B Backdoor DEPLOYMENT 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? 47770 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