Mistral 7B MoEified 8x by kalomaze

 ยป  All LLMs  ยป  kalomaze  ยป  Mistral 7B MoEified 8x   URL Share it on

  Arxiv:2303.01610   Autotrain compatible   Endpoints compatible   F16   Ggml   Gguf   License:apache-2.0   Mixtral   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Mistral 7B MoEified 8x 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  
Mistral 7B MoEified 8x (kalomaze/Mistral-7b-MoEified-8x)

Best Alternatives to Mistral 7B MoEified 8x

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Multimerge 12B MoE76.6832K / 25.8 GB12810
Calmex26merge 12B MoE76.632K / 25.8 GB13470
CeptrixBeagle 12B MoE76.3932K / 25.8 GB13521
Neuraljack 12B MoE76.2432K / 25.8 GB13440
...ltimerge Neurallaymons 12B MoE76.2132K / 25.8 GB13550
WestLakeMultiverse 12B MoE76.1232K / 25.8 GB13530
WestLakeLaser 12B MoE75.8932K / 25.8 GB13580
JupiterINEX12 12B MoE75.7732K / 25.8 GB12670
Multimaster 7B V675.6632K / 142.5 GB21671
Lumina 475.5932K / 37.1 GB10160
Note: green Score (e.g. "73.2") means that the model is better than kalomaze/Mistral-7b-MoEified-8x.

Mistral 7B MoEified 8x Parameters and Internals

LLM NameMistral 7B MoEified 8x
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM14.6 GB
Updated2024-06-24
Maintainerkalomaze
Model Typemixtral
Model Files  14.5 GB   1.0 GB: 1-of-15   1.0 GB: 2-of-15   1.0 GB: 3-of-15   1.0 GB: 4-of-15   1.0 GB: 5-of-15   1.0 GB: 6-of-15   1.0 GB: 7-of-15   1.0 GB: 8-of-15   1.0 GB: 9-of-15   1.0 GB: 10-of-15   1.0 GB: 11-of-15   1.0 GB: 12-of-15   1.0 GB: 13-of-15   1.0 GB: 14-of-15   0.6 GB: 15-of-15
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801