NeMoist 21B V1a by BeaverAI

 ยป  All LLMs  ยป  BeaverAI  ยป  NeMoist 21B V1a   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Mistral   Region:us   Safetensors

NeMoist 21B V1a Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

NeMoist 21B V1a Parameters and Internals

LLM NameNeMoist 21B V1a
Repository ๐Ÿค—https://huggingface.co/BeaverAI/NeMoist-21B-v1a 
Model Size21b
Required VRAM40.8 GB
Updated2024-10-30
MaintainerBeaverAI
Model Typemistral
Model Files  4.9 GB: 1-of-9   4.9 GB: 2-of-9   4.9 GB: 3-of-9   4.9 GB: 4-of-9   4.9 GB: 5-of-9   4.9 GB: 6-of-9   4.9 GB: 7-of-9   4.9 GB: 8-of-9   1.6 GB: 9-of-9
Model ArchitectureMistralForCausalLM
Context Length1024000
Model Max Length1024000
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16
NeMoist 21B V1a (BeaverAI/NeMoist-21B-v1a)

Best Alternatives to NeMoist 21B V1a

Best Alternatives
Context / RAM
Downloads
Likes
Theia 21B V21000K / 40.8 GB7925
Moist Theia 21B1000K / 40.8 GB321
Theia 21B V11000K / 40.8 GB1827
NeMoria 21B1000K / 40.9 GB2312
Blendy0011000K / 40.8 GB100
Theia 21B V1 Pretrained1000K / 40.8 GB100
NeMoist 21B V0.51000K / 40.8 GB60
Codestral 21B Pruned32K / 43.1 GB352
Note: green Score (e.g. "73.2") means that the model is better than BeaverAI/NeMoist-21B-v1a.

Rank the NeMoist 21B V1a 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? 37405 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803