Sparsetral 16x7B V2 by serpdotai

 ยป  All LLMs  ยป  serpdotai  ยป  Sparsetral 16x7B V2   URL Share it on

  Arxiv:2401.02731   Autotrain compatible   Conversational   Custom code   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Moe   Region:us   Safetensors   Sharded   Sparsetral   Tensorflow

Sparsetral 16x7B V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sparsetral 16x7B V2 (serpdotai/sparsetral-16x7B-v2)

Sparsetral 16x7B V2 Parameters and Internals

LLM NameSparsetral 16x7B V2
Repository ๐Ÿค—https://huggingface.co/serpdotai/sparsetral-16x7B-v2 
Model Size9.4b
Required VRAM18.7 GB
Updated2024-12-26
Maintainerserpdotai
Model Typesparsetral
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   3.9 GB: 4-of-4
Supported Languagesen
Model Architecturemodeling_sparsetral.MistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Sparsetral 16x7B V2

Best Alternatives
Context / RAM
Downloads
Likes
Sparsetral 16x7B V2 SPIN Iter132K / 18.7 GB2113
Sparsetral 16x7B V2 SPIN Iter032K / 18.7 GB158
...s Sparsetral Mistral 16x7b MoE32K / 18.7 GB114

Rank the Sparsetral 16x7B V2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40248 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217