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

BigLlama 3.1 1T Instruct by mlabonne

 »  All LLMs  »  mlabonne  »  BigLlama 3.1 1T Instruct   URL Share it on

  156   
  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/BigLlama-3.1-1T-Instruct 

BigLlama 3.1 1T Instruct Benchmarks

LLME Score: 0.22815
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BigLlama 3.1 1T Instruct (mlabonne/BigLlama-3.1-1T-Instruct)

BigLlama 3.1 1T Instruct Parameters and Internals

Model Type 
creative writing
Use Cases 
Primary Use Cases:
creative writing
Limitations:
Experimental model; use at your own risk.
Additional Notes 
This is an experimental self-merged model. The configuration uses a YAML setup with a passthrough merge method. The model's parameters were calculated using a Python script included in the notes.
Training Details 
Methodology:
Merge of Meta-Llama-3.1-405B-Instruct and Meta-Llama-3-120B-Instruct using mergekit's passthrough merge method.
LLM NameBigLlama 3.1 1T Instruct
Repository 🤗https://huggingface.co/mlabonne/BigLlama-3.1-1T-Instruct 
Base Model(s)  meta-llama/Meta-Llama-3.1-681B-Instruct   meta-llama/Meta-Llama-3.1-681B-Instruct
Merged ModelYes
Model Size681b
Required VRAM186.1 GB
Updated2025-02-05
Maintainermlabonne
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB: 1-of-481   4.2 GB: 2-of-481   3.5 GB: 3-of-481   4.7 GB: 4-of-481   4.7 GB: 5-of-481   3.5 GB: 6-of-481   4.7 GB: 7-of-481   3.5 GB: 8-of-481   3.5 GB: 9-of-481   4.2 GB: 10-of-481   3.5 GB: 11-of-481   3.5 GB: 12-of-481   4.7 GB: 13-of-481   4.7 GB: 14-of-481   3.5 GB: 15-of-481   4.7 GB: 16-of-481   4.7 GB: 17-of-481   3.5 GB: 18-of-481   4.7 GB: 19-of-481   4.7 GB: 20-of-481   3.5 GB: 21-of-481   3.5 GB: 22-of-481   3.5 GB: 23-of-481   4.6 GB: 24-of-481   4.2 GB: 25-of-481   3.5 GB: 26-of-481   4.7 GB: 27-of-481   4.7 GB: 28-of-481   3.5 GB: 29-of-481   4.7 GB: 30-of-481   4.7 GB: 31-of-481   3.5 GB: 32-of-481   4.7 GB: 33-of-481   4.7 GB: 34-of-481   3.5 GB: 35-of-481   4.7 GB: 36-of-481   4.7 GB: 37-of-481   3.5 GB: 38-of-481   4.7 GB: 39-of-481   4.7 GB: 40-of-481   4.7 GB: 41-of-481   3.5 GB: 42-of-481   3.5 GB: 43-of-481   4.2 GB: 44-of-481   3.5 GB: 45-of-481
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.0
Vocabulary Size128256
Torch Data Typebfloat16

Rank the BigLlama 3.1 1T Instruct 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