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

Sakura SOLAR Instruct DPO V2 by kyujinpy

 »  All LLMs  »  kyujinpy  »  Sakura SOLAR Instruct DPO V2   URL Share it on

  1797   
  Autotrain compatible   Conversational Dataset:argilla/distilabel-mat...   En   Endpoints compatible   Instruct   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct-DPO-v2 

Sakura SOLAR Instruct DPO V2 Benchmarks

ARC: 70.9 vs 96.7 (so35)-26.7%
HellaSwag: 88.41 vs 95.3 (gpt4)-7.2%
MMLU: 66.48 vs 88.3 (so35)-24.7%
TruthfulQA: 71.86 vs 59 (gpt4)21.8%
WinoGrande: 83.43 vs 87.5 (gpt4)-4.7%
GSM8K: 63.76 vs 96.4 (so35)-33.9%
LLME Score: 0.15585
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sakura SOLAR Instruct DPO V2 (kyujinpy/Sakura-SOLAR-Instruct-DPO-v2)
🌟 Advertise your project 🚀

Sakura SOLAR Instruct DPO V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
The model follows the developments in the field by utilizing the DPO method.
Training Details 
Data Sources:
argilla/distilabel-math-preference-dpo
Methodology:
DPO method
LLM NameSakura SOLAR Instruct DPO V2
Repository 🤗https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct-DPO-v2 
Model Size10.7b
Required VRAM21.4 GB
Updated2025-08-18
Maintainerkyujinpy
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   1.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Sakura SOLAR Instruct DPO V2

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB54
SOLAR 10.7B V1.0 Instruct 16K16K / 21.4 GB632
SauerkrautLM SOLAR Instruct8K / 21.4 GB195546
MetaModelv28K / 21.4 GB19610
Kazemi 1.2 Solar8K / 21.4 GB00
SOLAR 10.7B Instruct V1.04K / 21.4 GB71584630
Solarmer34K / 21.4 GB50
Somer24K / 21.4 GB50
Somer4K / 21.4 GB50
...arbonVillain En 10.7B V2 Slerp4K / 21.4 GB131620
Note: green Score (e.g. "73.2") means that the model is better than kyujinpy/Sakura-SOLAR-Instruct-DPO-v2.

Rank the Sakura SOLAR Instruct DPO V2 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? 50729 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