Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
NousResearch
|
|---|---|
| Company | NousResearch |
| Release Date | 2023-07-18 |
| Parameters (B) | 70 |
| Architecture | Transformer |
| Context Window | 4096 |
| Input Modalities | text |
| Open Source | Yes |
| License | |
| Score | 0 |
| VRAM (GB) | 140 |
| Compute | 2x NVIDIA A100 80GB (FP16); ~40GB with 4-bit quantization |
| Benchmark: AGIEval | 54.2 |
| Benchmark: ARC | 57.4 |
| Benchmark: Arena-Elo | 1170.4 |
| Benchmark: BBH | 51.2 |
| Benchmark: GPQA-Diamond | 26.3 |
| Benchmark: GSM8K | 56.8 |
| Benchmark: HellaSwag | 85.3 |
| Benchmark: HumanEval | 89 |
| Benchmark: IFEval | 49.6 |
| Benchmark: MATH | 13.5 |
| Benchmark: MBPP | 83.1 |
| Benchmark: MMLU | 68.9 |
| Benchmark: MMLU-Pro | 37.5 |
| Benchmark: TruthfulQA | 64.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |