Arxiv:2101.09635 Autotrain compatible Custom code En Endpoints compatible Id Km Lo Mpt Ms My Region:us Safetensors Ta Th Tl Vi Zh
Model Card on HF 🤗: https://huggingface.co/aisingapore/SEA-LION-v1-3B
SEA LION V1 3B 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)
SEA LION V1 3B Parameters and Internals
| LLM Name | SEA LION V1 3B |
| Repository 🤗 | https://huggingface.co/aisingapore/SEA-LION-v1-3B |
| Model Size | 3b |
| Required VRAM | 6.4 GB |
| Updated | 2025-04-28 |
| Maintainer | aisingapore |
| Model Type | mpt |
| Model Files | |
| Supported Languages | en zh id ms tl my vi th lo km ta |
| Model Architecture | MPTForCausalLM |
| License | mit |
| Transformers Version | 4.34.1 |
| Tokenizer Class | SEABPETokenizer |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to SEA LION V1 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Replit Code V1.5 3B | 0K / 6.6 GB | 1760 | 294 |
| Sea Lion 3B | 0K / 6.4 GB | 778 | 17 |
| Code Millenials 3B | 0K / 5.2 GB | 4 | 1 |
| Replit Code V1 3B | 0K / 10.4 GB | 597 | 732 |
| Mpt 3B 8K Instruct | 0K / 6.9 GB | 2 | 3 |
| Glaive Function Calling V1 | 0K / 10.4 GB | 46 | 68 |
| ...aive Function Calling V2 Small | 0K / 10.4 GB | 60 | 14 |
| Evol Replit V1 | 0K / 10.4 GB | 11 | 8 |
| Replit V2 CodeInstruct 3B | 0K / 10.4 GB | 20 | 72 |
| Replit CodeInstruct V3 | 0K / 10.4 GB | 5 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than aisingapore/SEA-LION-v1-3B .
Rank the SEA LION V1 3B 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? 46763 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227