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

RYS Llama3.1 Large by dnhkng

 »  All LLMs  »  dnhkng  »  RYS Llama3.1 Large   URL Share it on

  2999   
  Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dnhkng/RYS-Llama3.1-Large 

RYS Llama3.1 Large Benchmarks

MMLU Pro: 47.21
GPQA: 16.55
MUSR: 17.09
BBH: 55.41
IFEval: 84.92 vs 88 (so35)-3.5%
MATH Lvl 5: 30.44
LLME Score: 0.37117
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
RYS Llama3.1 Large (dnhkng/RYS-Llama3.1-Large)

RYS Llama3.1 Large Parameters and Internals

Model Type 
text-generation
Additional Notes 
This is a new kind of model optimization. The model is based on Meta's Llama-3 70B Instruct. A paper on the technique is currently being written.
LLM NameRYS Llama3.1 Large
Repository 🤗https://huggingface.co/dnhkng/RYS-Llama3.1-Large 
Model Size81.7b
Required VRAM162.3 GB
Updated2025-02-05
Maintainerdnhkng
Model Typellama
Model Files  5.1 GB: 1-of-32   5.1 GB: 2-of-32   5.1 GB: 3-of-32   5.1 GB: 4-of-32   5.1 GB: 5-of-32   5.1 GB: 6-of-32   5.1 GB: 7-of-32   5.1 GB: 8-of-32   5.1 GB: 9-of-32   5.1 GB: 10-of-32   5.1 GB: 11-of-32   5.1 GB: 12-of-32   5.1 GB: 13-of-32   5.1 GB: 14-of-32   5.1 GB: 15-of-32   5.1 GB: 16-of-32   5.1 GB: 17-of-32   5.1 GB: 18-of-32   5.1 GB: 19-of-32   5.1 GB: 20-of-32   5.1 GB: 21-of-32   5.1 GB: 22-of-32   5.1 GB: 23-of-32   5.1 GB: 24-of-32   5.1 GB: 25-of-32   5.1 GB: 26-of-32   5.1 GB: 27-of-32   5.1 GB: 28-of-32   5.1 GB: 29-of-32   5.1 GB: 30-of-32   5.1 GB: 31-of-32   4.2 GB: 32-of-32
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.42.3
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Rank the RYS Llama3.1 Large 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? 42577 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