Sailor 1.8B is an open-source language model by sail. Features: 1.8b LLM, VRAM: 3.7GB, Context: 8K, License: apache-2.0, HF Score: 36.6, LLM Explorer Score: 0.17, Arc: 33.1, HellaSwag: 57.1, MMLU: 30.4, TruthfulQA: 37.8, WinoGrande: 58.4, GSM8K: 2.7.
Arxiv:2404.03608 Base model:finetune:qwen/qwen1... Base model:qwen/qwen1.5-1.8b Conversational Dataset:allenai/madlad-400 Dataset:cc100 Dataset:cerebras/slimpajama-62... Dataset:skywork/skypile-150b En Id Lo Model-index Ms Multilingual Qwen2 Region:us Safetensors Sailor Sea Th Vi Zh
Model Card on HF 🤗: https://huggingface.co/sail/Sailor-1.8B
Sailor 1.8B Benchmarks
ARC: 33.11 vs 96.7 (so35)-65.8%
HellaSwag: 57.06 vs 95.3 (gpt4)-40.1%
MMLU: 30.44 vs 88.3 (so35)-65.5%
TruthfulQA: 37.81 vs 59 (gpt4)-35.9%
WinoGrande: 58.41 vs 87.5 (gpt4)-33.2%
GSM8K: 2.73 vs 96.4 (so35)-97.2%
LLME Score: 0.16577
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Sailor 1.8B Parameters and Internals
| LLM Name | Sailor 1.8B |
| Repository 🤗 | https://huggingface.co/sail/Sailor-1.8B |
| Base Model(s) | |
| Model Size | 1.8b |
| Required VRAM | 3.7 GB |
| Updated | 2026-04-04 |
| Maintainer | sail |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en zh id th vi ms lo |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Sailor 1.8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dhanishtha | 128K / 3.5 GB | 82 | 2 |
| LaConfiance PRYMMAL ECE TW3 | 128K / 7.1 GB | 5 | 0 |
| Reyna Mini 1.8B V0.1 | 32K / 3.7 GB | 109 | 2 |
| Qwen1.5 1.8B Chat | 32K / 3.7 GB | 73672 | 73 |
| Qwen1.5 1.8B | 32K / 3.7 GB | 24781 | 59 |
| Colegium Ai 1.8B | 32K / 3.7 GB | 15 | 0 |
| Qwen Fine Tuned V0 | 32K / 3.7 GB | 53 | 0 |
| Qwen1.5 1.8B Seed Sft | 32K / 3.7 GB | 6 | 0 |
| Neural Chat Mini V2.2 1.8B | 32K / 3.7 GB | 9 | 6 |
| Qwen1.5 Wukong 1.8B | 32K / 3.7 GB | 5 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor-1.8B .
Rank the Sailor 1.8B Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a