LLM EXPLORER 59,420 MODELS INDEXED

Sailor2 20B Chat by sail

By sail · 209 downloads
HF Repo ↗ Copy URL

Sailor2 20B Chat is an open-source language model by sail. Features: 20b LLM, VRAM: 38.6GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

  Arxiv:2502.12982 Base model:finetune:sail/sailo...   Base model:sail/sailor2-20b   Chat   Conversational   En   Endpoints compatible   Id   Instruct   Instruction   Jv   Km   Lo   Ms   Multilingual   My   Qwen2   Region:us   Safetensors   Sailor   Sea   Sft   Sharded   Su   Tensorflow   Th   Tl   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/sail/Sailor2-20B-Chat 

Sailor2 20B Chat Parameters and Internals

LLM NameSailor2 20B Chat
Repository 🤗https://huggingface.co/sail/Sailor2-20B-Chat 
Base Model(s)  Sailor2 20B   sail/Sailor2-20B
Model Size20b
Required VRAM38.6 GB
Updated2026-08-04
Maintainersail
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-8   5.0 GB: 2-of-8   5.0 GB: 3-of-8   5.0 GB: 4-of-8   5.0 GB: 5-of-8   5.0 GB: 6-of-8   5.0 GB: 7-of-8   3.6 GB: 8-of-8
Supported Languagesen zh id th vi ms lo my jv km su tl
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Sailor2 20B Chat

Model
Likes
Downloads
VRAM
Sailor2 20B Chat GGUF2717 GB