KIT 5.8B by snunlp

 ยป  All LLMs  ยป  snunlp  ยป  KIT 5.8B   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Endpoints compatible   Gpt neox   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/snunlp/KIT-5.8b 

KIT 5.8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
KIT 5.8B (snunlp/KIT-5.8b)

KIT 5.8B Parameters and Internals

LLM NameKIT 5.8B
Repository ๐Ÿค—https://huggingface.co/snunlp/KIT-5.8b 
Model Size5.8b
Required VRAM23.4 GB
Updated2024-12-21
Maintainersnunlp
Model Typegpt_neox
Model Files  4.8 GB: 1-of-5   4.8 GB: 2-of-5   4.8 GB: 3-of-5   4.8 GB: 4-of-5   4.2 GB: 5-of-5
Model ArchitectureGPTNeoXForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.37.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size30080
Torch Data Typefloat32

Best Alternatives to KIT 5.8B

Best Alternatives
Context / RAM
Downloads
Likes
Ai Script22K / 3.8 GB70
Ai Script2K / 3.8 GB50
KIT 5.8B2K / 23.5 GB48700
KoAlpaca Polyglot 5.8B2K / 11.7 GB690960
Polyglot Ko 5.8B Inst2K / 23.6 GB48810
ChatSKKU5.8B2K / 11.3 GB49130
KoQuality Polyglot 5.8B2K / 23.6 GB49203
Polyglot Ko 5.8B Inst All2K / 23.6 GB25302
...olyglot 5.8B V2 Koalpaca V1.1B2K / 23.6 GB49280
...olyglot 5.8B V2 Koalpaca V1.1B2K / 23.6 GB49080
Note: green Score (e.g. "73.2") means that the model is better than snunlp/KIT-5.8b.

Rank the KIT 5.8B 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? 40013 in total.

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