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

Sd2 by Delta-Vector

 »  All LLMs  »  Delta-Vector  »  Sd2   URL Share it on

  210   

Sd2 is an open-source language model by Delta-Vector. Features: 70b LLM, VRAM: 215.4GB, Context: 128K, License: llama3.3, LLM Explorer Score: 0.2.

  70b   Autotrain compatible   Axolotl Base model:finetune:sao10k/lla... Base model:sao10k/llama-3.3-70...   Conversational   Creative-writing Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:neweden/bluesky-10k-co... Dataset:neweden/books-v2-share... Dataset:neweden/creative writi... Dataset:neweden/deepseek-v3-rp... Dataset:neweden/deepseekrp-fil... Dataset:neweden/final-alpindal... Dataset:neweden/light-novels-r... Dataset:neweden/limarp-complex... Dataset:neweden/opencai-shareg... Dataset:neweden/pippa-mega-fil... Dataset:neweden/rp-logs-v2-exp... Dataset:neweden/storium-prefix... Dataset:neweden/vanilla-backro... Dataset:pocketdoc/dans-failure... Dataset:pocketdoc/dans-persona...   En   Endpoints compatible   Finetuned   Llama   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Edens-Gate/sd2 

Sd2 Benchmarks

LLME Score: 0.19929
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sd2 (Edens-Gate/sd2)
🌟 Advertise your project 🚀

Sd2 Parameters and Internals

LLM NameSd2
Repository 🤗https://huggingface.co/Edens-Gate/sd2 
Base Model(s)  Sao10K/Llama-3.3-70B-Vulpecula-r1   Sao10K/Llama-3.3-70B-Vulpecula-r1
Model Size70b
Required VRAM215.4 GB
Updated2025-06-23
MaintainerDelta-Vector
Model Typellama
Model Files  4.2 GB: 1-of-62   4.2 GB: 2-of-62   4.4 GB: 3-of-62   4.4 GB: 4-of-62   5.0 GB: 5-of-62   4.4 GB: 6-of-62   4.4 GB: 7-of-62   5.0 GB: 8-of-62   4.4 GB: 9-of-62   4.4 GB: 10-of-62   5.0 GB: 11-of-62   4.4 GB: 12-of-62   4.4 GB: 13-of-62   5.0 GB: 14-of-62   4.4 GB: 15-of-62   4.4 GB: 16-of-62   5.0 GB: 17-of-62   4.4 GB: 18-of-62   4.4 GB: 19-of-62   5.0 GB: 20-of-62   4.4 GB: 21-of-62   4.4 GB: 22-of-62   5.0 GB: 23-of-62   4.4 GB: 24-of-62   4.4 GB: 25-of-62   5.0 GB: 26-of-62   4.4 GB: 27-of-62   4.4 GB: 28-of-62   5.0 GB: 29-of-62   4.4 GB: 30-of-62   4.7 GB: 31-of-62   4.7 GB: 32-of-62   4.4 GB: 33-of-62   4.4 GB: 34-of-62   5.0 GB: 35-of-62   4.4 GB: 36-of-62   4.4 GB: 37-of-62   5.0 GB: 38-of-62   4.4 GB: 39-of-62   4.4 GB: 40-of-62   5.0 GB: 41-of-62   4.4 GB: 42-of-62   4.4 GB: 43-of-62   5.0 GB: 44-of-62   4.4 GB: 45-of-62   4.4 GB: 46-of-62   5.0 GB: 47-of-62
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.3
Context Length131072
Model Max Length131072
Transformers Version4.49.0
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Sd2

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB82864
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB21122
Llama3 Function Calling 1048K1024K / 141.9 GB31
...a 3 70B Instruct Gradient 524K512K / 141.9 GB3623
...a 3 70B Instruct Gradient 262K256K / 141.9 GB2156
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB123
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB70
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB133
Yi 70B 200K RPMerge Franken195K / 142.4 GB61

Rank the Sd2 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? 54120 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