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 681B Instruct by mlabonne

 »  All LLMs  »  mlabonne  »  BigLlama 3.1 681B Instruct   URL Share it on

  25   
  Merged Model   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/BigLlama-3.1-681B-Instruct 

BigLlama 3.1 681B Instruct Benchmarks

LLME Score: 0.21879
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 681B Instruct (mlabonne/BigLlama-3.1-681B-Instruct)

BigLlama 3.1 681B Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Applications:
creative writing
Additional Notes 
This is an experimental self-merge using Meta-Llama-3.1-405B-Instruct and was created with the use of mergekit. It is suggested to use the Llama 3 chat template for optimal performance.
LLM NameBigLlama 3.1 681B Instruct
Repository 🤗https://huggingface.co/mlabonne/BigLlama-3.1-681B-Instruct 
Base Model(s)  meta-llama/Meta-Llama-3.1-405B-Instruct   meta-llama/Meta-Llama-3.1-405B-Instruct
Merged ModelYes
Model Size405b
Required VRAM190.8 GB
Updated2024-12-30
Maintainermlabonne
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB: 1-of-322   4.2 GB: 2-of-322   3.5 GB: 3-of-322   4.7 GB: 4-of-322   4.7 GB: 5-of-322   3.5 GB: 6-of-322   4.7 GB: 7-of-322   3.5 GB: 8-of-322   3.5 GB: 9-of-322   4.2 GB: 10-of-322   3.5 GB: 11-of-322   3.5 GB: 12-of-322   4.7 GB: 13-of-322   4.7 GB: 14-of-322   3.5 GB: 15-of-322   4.7 GB: 16-of-322   4.7 GB: 17-of-322   3.5 GB: 18-of-322   4.7 GB: 19-of-322   4.7 GB: 20-of-322   3.5 GB: 21-of-322   4.7 GB: 22-of-322   4.7 GB: 23-of-322   4.7 GB: 24-of-322   4.7 GB: 25-of-322   3.5 GB: 26-of-322   4.7 GB: 27-of-322   4.7 GB: 28-of-322   3.5 GB: 29-of-322   4.7 GB: 30-of-322   4.7 GB: 31-of-322   3.5 GB: 32-of-322   4.7 GB: 33-of-322   4.7 GB: 34-of-322   3.5 GB: 35-of-322   4.7 GB: 36-of-322   4.7 GB: 37-of-322   3.5 GB: 38-of-322   4.7 GB: 39-of-322   4.7 GB: 40-of-322   3.5 GB: 41-of-322   4.7 GB: 42-of-322   4.7 GB: 43-of-322   3.5 GB: 44-of-322   4.7 GB: 45-of-322
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to BigLlama 3.1 681B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3.1 405B Instruct128K / 186 GB55654473
Llama 3.1 405B Instruct128K / 183.1 GB34745555
...ta Llama 3.1 405B Instruct FP8128K / 197.6 GB55370165
Llama 3.1 405B Instruct FP8128K / 193.4 GB36775184
INTELLECT 1 Instruct8K / 20.5 GB2993115
...ama 3.1 405B Instruct Bnb 4bit128K / 214.3 GB3034
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/BigLlama-3.1-681B-Instruct.

Rank the BigLlama 3.1 681B 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? 40476 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