Sailor 0.5B by sail

 ยป  All LLMs  ยป  sail  ยป  Sailor 0.5B   URL Share it on

  Arxiv:2404.03608   Autotrain compatible   Base model:qwen/qwen1.5-0.5b   Conversational   Dataset:allenai/madlad-400   Dataset:cc100 Dataset:cerebras/slimpajama-62...   Dataset:skywork/skypile-150b   En   Id   License:apache-2.0   Lo   Model-index   Ms   Multilingual   Qwen2   Region:us   Safetensors   Sailor   Sea   Th   Vi   Zh

Sailor 0.5B Benchmarks

Sailor 0.5B Parameters and Internals

LLM NameSailor 0.5B
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Qwen/Qwen1.5-0.5B   Qwen/Qwen1.5-0.5B
Model Size0.5b
Required VRAM1.2 GB
Model Typeqwen2
Model Files  1.2 GB
Supported Languagesen zh id th vi ms lo
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Sailor 0.5B (sail/Sailor-0.5B)

Best Alternatives to Sailor 0.5B

Best Alternatives
HF Rank
Qwen2 0.5B0.4128K / 1 GB9463254
Qwen2 Wukong 0.5B0.3128K / 1.3 GB1436
Dolphin 2.9.3 Qwen2 0.5B0.3128K / 1 GB7233
Qwen2 0.5B0.3128K / 1 GB10271
Qwen2 0.5B Fncl 20.3128K / 1 GB2140
Tag2prompt Qwen2 0.5B V0.10.3128K / 1 GB1551
Qwen2 0.5B Fncl0.3128K / 1 GB861
Qwen2 0.5B Tldr Sft0.3128K / 2 GB440
Qwen Resave Vikhr0.3128K / 1 GB600
Oneirogen 0.5B0.3128K / 1 GB941
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor-0.5B.

Rank the Sailor 0.5B 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? 34211 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601