Model Card on HF 🤗: https://huggingface.co/lt-asset/nova-1.3b
Nova 1.3B Benchmarks
MMLU Pro: 1.58
MUSR: 3.76
BBH: 4.44
IFEval: 12.14 vs 88 (so35)-86.2%
MATH Lvl 5: 1.21
LLME Score: 0.17252
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)
Nova 1.3B Parameters and Internals
| LLM Name | Nova 1.3B |
| Repository 🤗 | https://huggingface.co/lt-asset/nova-1.3b |
| Model Size | 1.3b |
| Required VRAM | 2.7 GB |
| Updated | 2025-02-22 |
| Maintainer | lt-asset |
| Model Type | llama |
| Model Files | |
| Model Architecture | NovaForCausalLM |
| License | bsd-3-clause-clear |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 32280 |
| Torch Data Type | bfloat16 |
Rank the Nova 1.3B 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227