Arxiv:2502.12982 Autotrain compatible Base model:finetune:sail/sailo... Base model:sail/sailor2-8b Conversational En Endpoints compatible Id Jv Km Lo Ms Multilingual My Qwen2 Region:us Safetensors Sailor Sea Sharded Su Tensorflow Th Tl Vi Zh
Model Card on HF 🤗: https://huggingface.co/sail/Sailor2-L-8B
Sailor2 L 8B Benchmarks
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)
Sailor2 L 8B Parameters and Internals
| LLM Name | Sailor2 L 8B |
| Repository 🤗 | https://huggingface.co/sail/Sailor2-L-8B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 17.1 GB |
| Updated | 2025-09-23 |
| Maintainer | sail |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en zh id th vi ms lo my jv km su tl |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.39.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Sailor2 L 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SJT 8B | 128K / 17.8 GB | 3 | 1 |
| Sailor2 8B Chat | 4K / 17.1 GB | 1251 | 20 |
| SupaMATH | 128K / 5.6 GB | 6 | 0 |
| BloomVN 8B Chat | 32K / 17.1 GB | 4 | 4 |
| Sailor2 8B Chat Uncensored | 32K / 17.1 GB | 4 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor2-L-8B .
Rank the Sailor2 L 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124