Sailor 7B Chat is an open-source language model by sail. Features: 7b LLM, VRAM: 15.4GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14, Arc: 52.3, HellaSwag: 75, MMLU: 56.2, GSM8K: 30.4.
Sailor 7B Chat Parameters and Internals
| Model Type | | multilingual, chat, instruction |
|
| Supported Languages | | en (proficient), zh (proficient), id (proficient), th (proficient), vi (proficient), ms (proficient), lo (proficient) |
|
| Training Details |
| Data Sources: | | SlimPajama, SkyPile, CC100, MADLAD-400 |
|
| Data Volume: | |
| Methodology: | | Continual pre-training with aggressive data deduplication and careful cleaning |
|
|
| LLM Name | Sailor 7B Chat |
| Repository 🤗 | https://huggingface.co/sail/Sailor-7B-Chat |
| Base Model(s) | Sailor 7B sail/Sailor-7B |
| Model Size | 7b |
| Required VRAM | 15.4 GB |
| Updated | 2026-07-05 |
| Maintainer | sail |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | 15.4 GB |
| Supported Languages | en zh id th vi ms lo |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Sailor 7B Chat
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor-7B-Chat.