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

Control 8B V1.1 by Delta-Vector

 »  All LLMs  »  Delta-Vector  »  Control 8B V1.1   URL Share it on

  5   
  Merged Model   Chat Dataset:huggingfaceh4/ultrafee... Dataset:neweden/opencai-shareg... Dataset:neweden/roleplay-logs-...   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Control-8B-V1.1 

Control 8B V1.1 Benchmarks

MMLU Pro: 30.5
GPQA: 7.61
MUSR: 11.23
BBH: 28.73
IFEval: 56.97 vs 88 (so35)-35.3%
MATH Lvl 5: 12.76
LLME Score: 0.25314
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Control 8B V1.1 (Delta-Vector/Control-8B-V1.1)
🌟 Advertise your project 🚀

Control 8B V1.1 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
chat, role-play
Applications:
text generation, AI assistant
Primary Use Cases:
character-based role-play
Limitations:
not suitable for NSFW content
Considerations:
Ensure contextual appropriateness for content.
Additional Notes 
Designed to be 'Short and Sweet'.
Supported Languages 
English (High)
Training Details 
Data Sources:
NewEden/OpenCAI-ShareGPT, NewEden/Roleplay-Logs-Sharegpt-Ngram-cleaned, HuggingFaceH4/ultrafeedback_binarized
Methodology:
Finetuned for 2 epochs using DPO
Context Length:
1024
Hardware Used:
4 x RTX 3090 GPUs, 1 x Nvidia T4 GPU
Input Output 
Input Format:
LLama-Instruct formatting
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use Euryale's or EVA system prompts for optimal performance.
LLM NameControl 8B V1.1
Repository 🤗https://huggingface.co/Delta-Vector/Control-8B-V1.1 
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2025-09-23
MaintainerDelta-Vector
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseagpl-3.0
Context Length131072
Model Max Length131072
Transformers Version4.45.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Control 8B V1.1

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1531120
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB03
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB10515
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB156156
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB404
Zero Llama 3.1 8B Beta61048K / 16.1 GB21
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB13

Rank the Control 8B V1.1 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? 51611 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