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 by Delta-Vector

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

  9   
  Chat 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 

Control 8B Benchmarks

MMLU Pro: 30.35
GPQA: 8.84
MUSR: 13.21
BBH: 29.16
IFEval: 54.9 vs 88 (so35)-37.6%
MATH Lvl 5: 13.9
LLME Score: 0.28282
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Control 8B (Delta-Vector/Control-8B)

Control 8B Parameters and Internals

Model Type 
AutoModelForCausalLM
Use Cases 
Primary Use Cases:
Chat, Text Generation
Additional Notes 
Model is described as "Short and Sweet", focusing on concise interactions.
Supported Languages 
En (English)
Training Details 
Data Sources:
NewEden/CharacterAI-logs-sharegpt-Ngram-Cleaned, NewEden/OpenCAI-ShareGPT
Methodology:
finetuned the model for 2 epochs
Context Length:
16384
Hardware Used:
4 x RTX 3090s
Input Output 
Input Format:
LLama-Instruct formatting
Accepted Modalities:
text
Performance Tips:
Recommend using either Euryale's or EVA's system prompt
LLM NameControl 8B
Repository 🤗https://huggingface.co/Delta-Vector/Control-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-04-23
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 Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Control 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB178094
UltraLong Thinking4192K / 16.1 GB652
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB121915
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB231138
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB101
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB24982679
A11024K / 16.1 GB8530
Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Control-8B.

Rank the Control 8B 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? 46599 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