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

GPT JT 6B V1 Float16 by ASID

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

 ยป  All LLMs  ยป  ASID  ยป  GPT JT 6B V1 Float16   URL Share it on

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

Rank the GPT JT 6B V1 Float16 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  
GPT JT 6B V1 Float16 (ASID/GPT-JT-6B-v1-float16)

Best Alternatives to GPT JT 6B V1 Float16

Best Alternatives
HF Rank
GPT J 6B Int8 Dynamic Inc0K /  GB62416
GPT J 6B Int8 Static Inc0K /  GB309
GPT J 6B Onnx0K /  GB350
GPT J 6B Adventure0K / 6.1 GB440
GPT J 6B Skein0K / 6.1 GB290
GPT J 6B Shakespeare0K / 6.2 GB51
GPT J 6B Buckland0K / 6.2 GB51
...T J 6B Pytorch Int8 Static Inc0K / 6.7 GB280
Lit 6B0K / 12.1 GB51354
Japanese Novel GPT J 6B0K / 12.1 GB45531

GPT JT 6B V1 Float16 Parameters and Internals

LLM NameGPT JT 6B V1 Float16
RepositoryOpen on ๐Ÿค— 
Model Size6b
Required VRAM24.3 GB
Model Typegptj
Model Files  9.9 GB: 1-of-3   9.8 GB: 2-of-3   4.6 GB: 3-of-3
Model ArchitectureGPTJForCausalLM
Transformers Version4.26.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50400
Initializer Range0.02
Torch Data Typefloat16
Activation Functiongelu_new
Attention Dropout0
Embedding Dropout0
Layer Norm Epsilon1.0E-5
Summary First Dropout0.1
Summary Typecls_index
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003