Autotrain compatible Convai Conversational Dataset:argilla/openhermes2.5-... Dataset:freedomintelligence/ev... Dataset:wikimedia/wikipedia En Endpoints compatible Id Instruct Qwen2 Region:us Safetensors Sharded Tensorflow
Nusantara 1.8B Indo Chat Benchmarks
ARC: 35.32 vs 96.7 (so35)-63.5%
HellaSwag: 56.32 vs 95.3 (gpt4)-40.9%
MMLU: 30.37 vs 88.3 (so35)-65.6%
TruthfulQA: 37.27 vs 59 (gpt4)-36.8%
WinoGrande: 59.75 vs 87.5 (gpt4)-31.7%
GSM8K: 3.34 vs 96.4 (so35)-96.5%
LLME Score: 0.24507
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)
Nusantara 1.8B Indo Chat Parameters and Internals
| LLM Name | Nusantara 1.8B Indo Chat |
| Repository 🤗 | https://huggingface.co/kalisai/Nusantara-1.8b-Indo-Chat |
| Model Size | 1.8b |
| Required VRAM | 3.7 GB |
| Updated | 2024-09-07 |
| Maintainer | kalisai |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | id en |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Nusantara 1.8B Indo Chat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Orca 2.0 Tau 1.8B | 32K / 3.7 GB | 260 | 8 |
| Neural Chat Mini V2.2 1.8B | 32K / 3.7 GB | 54 | 5 |
| Sailor 1.8B Chat | 32K / 3.7 GB | 722 | 4 |
| EGTLM Qwen1.5 1.8B Instruct | 32K / 3.7 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kalisai/Nusantara-1.8b-Indo-Chat .
Rank the Nusantara 1.8B Indo 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803