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

SOLAR 10B OrcaDPO Jawade by bhavinjawade

 »  All LLMs  »  bhavinjawade  »  SOLAR 10B OrcaDPO Jawade   URL Share it on

  826   
  Autotrain compatible   Conversational   Dataset:intel/orca dpo pairs   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bhavinjawade/SOLAR-10B-OrcaDPO-Jawade 

SOLAR 10B OrcaDPO Jawade Benchmarks

ARC: 71.16 vs 96.7 (so35)-26.4%
HellaSwag: 88.27 vs 95.3 (gpt4)-7.4%
MMLU: 66.12 vs 88.3 (so35)-25.1%
TruthfulQA: 71.57 vs 59 (gpt4)21.3%
WinoGrande: 83.66 vs 87.5 (gpt4)-4.4%
GSM8K: 64.82 vs 96.4 (so35)-32.8%
LLME Score: 0.18991
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SOLAR 10B OrcaDPO Jawade (bhavinjawade/SOLAR-10B-OrcaDPO-Jawade)

SOLAR 10B OrcaDPO Jawade Parameters and Internals

Additional Notes 
This model is an instruction finetuned version of the SOLAR-10.7B-Instruct-v1.0 model. It shows a slight improvement on OpenLLM Leaderboard benchmarks against its base version and a significant improvement over the SOLAR 10.7B.
Training Details 
Data Sources:
Intel/orca_dpo_pairs
Methodology:
Low-Rank Adaptation (LoRA)
LLM NameSOLAR 10B OrcaDPO Jawade
Repository 🤗https://huggingface.co/bhavinjawade/SOLAR-10B-OrcaDPO-Jawade 
Model Size10b
Required VRAM21.4 GB
Updated2024-12-22
Maintainerbhavinjawade
Model Typellama
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to SOLAR 10B OrcaDPO Jawade

Best Alternatives
Context / RAM
Downloads
Likes
Falcon3 10B Instruct32K / 20.5 GB290555
...ma 3 10B It Kor Extented Chang8K / 19.6 GB481113
EEVE 10b ORPO Trained V24K / 21.6 GB110
EEVE 10b ORPO Trained4K / 21.6 GB90
Falcon3 10B Instruct 1.58bit32K / 4 GB1068
...truct Gptqmodel 4bit Vortex V132K / 5.6 GB113
Note: green Score (e.g. "73.2") means that the model is better than bhavinjawade/SOLAR-10B-OrcaDPO-Jawade.

Rank the SOLAR 10B OrcaDPO Jawade 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? 40123 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 v20241217
  Support LLM Explorer