Arxiv:2404.03608 Autotrain compatible Base model:finetune:sail/sailo... Base model:sail/sailor-1.8b Chat Conversational Dataset:cohereforai/aya collec... Dataset:cohereforai/aya datase... Dataset:open-orca/openorca En Id Instruct Instruction Lo Ms Multilingual Qwen2 Region:us Safetensors Sailor Sea Sft Th Vi Zh
Model Card on HF 🤗: https://huggingface.co/sail/Sailor-1.8B-Chat
Sailor 1.8B Chat Benchmarks
ARC: 35.75 vs 96.7 (so35)-63%
HellaSwag: 57.12 vs 95.3 (gpt4)-40.1%
MMLU: 38.31 vs 88.3 (so35)-56.6%
TruthfulQA: 38.71 vs 59 (gpt4)-34.4%
WinoGrande: 59.12 vs 87.5 (gpt4)-32.4%
GSM8K: 3.56 vs 96.4 (so35)-96.3%
LLME Score: 0.23364
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 Chat Parameters and Internals
| LLM Name | Sailor 1.8B Chat |
| Repository 🤗 | https://huggingface.co/sail/Sailor-1.8B-Chat |
| Base Model(s) | |
| Model Size | 1.8b |
| Required VRAM | 3.7 GB |
| Updated | 2024-12-21 |
| Maintainer | sail |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| 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 1.8B Chat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Orca 2.0 Tau 1.8B | 32K / 3.7 GB | 454 | 9 |
| Neural Chat Mini V2.2 1.8B | 32K / 3.7 GB | 19 | 5 |
| EGTLM Qwen1.5 1.8B Instruct | 32K / 3.7 GB | 10 | 1 |
| Nusantara 1.8B Indo Chat | 8K / 3.7 GB | 505 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than sail/Sailor-1.8B-Chat .
Rank the Sailor 1.8B Chat 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? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217