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

ESFT Vanilla Lite by deepseek-ai

 »  All LLMs  »  deepseek-ai  »  ESFT Vanilla Lite   URL Share it on

  357   

ESFT Vanilla Lite is an open-source language model by deepseek-ai. Features: 15.7b LLM, VRAM: 31.4GB, Context: 4K, LLM Explorer Score: 0.15.

  Arxiv:2407.01906   Conversational   Custom code   Deepseek v2   Endpoints compatible   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/ESFT-vanilla-lite 

ESFT Vanilla Lite Benchmarks

LLME Score: 0.15092
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ESFT Vanilla Lite (deepseek-ai/ESFT-vanilla-lite)
🌟 Advertise your project 🚀

ESFT Vanilla Lite Parameters and Internals

Model Type 
Expert-Specialized Fine-Tuning
Additional Notes 
To use this model and specialized expert sets, refer to the scripts at the specified GitHub repository. Customized models used in the research can be found on Hugging Face.
LLM NameESFT Vanilla Lite
Repository 🤗https://huggingface.co/deepseek-ai/ESFT-vanilla-lite 
Model Size15.7b
Required VRAM31.4 GB
Updated2026-03-26
Maintainerdeepseek-ai
Model Typedeepseek_v2
Model Files  8.6 GB: 1-of-4   8.6 GB: 2-of-4   8.6 GB: 3-of-4   5.6 GB: 4-of-4
Model ArchitectureDeepseekV2ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typebfloat16

Best Alternatives to ESFT Vanilla Lite

Best Alternatives
Context / RAM
Downloads
Likes
...eepSeek Coder V2 Lite Instruct160K / 31.4 GB367294572
DeepSeek V2 Lite Chat160K / 31.4 GB811609135
DeepSeek V2 Lite160K / 31.4 GB246467168
...e Sft Math7k 1epoch 1e 4 Gamma160K / 31.4 GB80
KwaiCoder DS V2 Lite Base160K / 31.4 GB12587
Dsv2 Lite Coder Codeio Pp160K / 31.4 GB112
DeepSeek Coder V2 Lite Base160K / 31.4 GB2312105
...2 Lite Instruct FlashAttnPatch160K / 31.4 GB60
LunarAI160K / 31.4 GB50
...eek Coder V2 Lite Instruct AWQ160K / 9.1 GB34589
Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/ESFT-vanilla-lite.

Rank the ESFT Vanilla Lite 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? 52758 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer