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 |
tiiuae
|
|---|---|
| Company | tiiuae |
| Release Date | 2023-04-24 |
| Parameters (B) | 7 |
| Architecture | Decoder-only Transformer |
| Context Window | 2048 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | At least 16GB VRAM for bf16 inference on a single GPU; trained on 384x NVIDIA A100 40GB |
| Benchmark: ARC | 48.5 |
| Benchmark: BBH | 32.5 |
| Benchmark: GPQA | 24.5 |
| Benchmark: GPQA-Diamond | 25.2 |
| Benchmark: GSM8K | 4.6 |
| Benchmark: HellaSwag | 78.1 |
| Benchmark: IFEval | 24.6 |
| Benchmark: MATH | 1.7 |
| Benchmark: MBPP | 10.2 |
| Benchmark: MMLU | 35 |
| Benchmark: MMLU-Pro | 11.2 |
| Benchmark: TruthfulQA | 34.3 |
| Pricing (Input) | — |
| Pricing (Output) | — |