LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

SynthIA 7B V1.5 by migtissera

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  migtissera  ยป  SynthIA 7B V1.5   URL Share it on

  Autotrain compatible   En   Endpoints compatible   License:apache-2.0   Mistral   Pytorch   Region:us   Sharded

SynthIA 7B V1.5 Benchmarks

Rank the SynthIA 7B V1.5 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  
SynthIA 7B V1.5 (migtissera/SynthIA-7B-v1.5)

Quantized Models of the SynthIA 7B V1.5

Model
Likes
Downloads
VRAM
SynthIA 7B V1.5 GGUF623 GB

Best Alternatives to SynthIA 7B V1.5

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Ogno Monarch Jaskier Merge 7B76.4332K / 14.5 GB1082
Jaskier 7B DPO V5.676.4132K / 14.4 GB30212
MonaTrix V476.3832K / 14.5 GB01
Jaskier 7B DPO V6.176.3632K / 14.4 GB213
OGNO 7B76.3432K / 14.4 GB103616
Omningotex 7B Slerp76.3332K / 14.4 GB6123
StrangeMerges 25 7B Dare Ties76.3332K / 14.4 GB1200
DPO Binarized NeutrixOmnibe 7B76.3132K / 14.4 GB5342
OgnoMonarch 7B76.332K / 14.5 GB1680
StrangeMerges 21 7B Slerp76.2932K / 14.4 GB6580
Note: green Score (e.g. "73.2") means that the model is better than migtissera/SynthIA-7B-v1.5.

SynthIA 7B V1.5 Parameters and Internals

LLM NameSynthIA 7B V1.5
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM14.4 GB
Updated2024-02-28
Maintainermigtissera
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003