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 |
bigscience
|
|---|---|
| Company | bigscience |
| Release Date | 2022-09-27 |
| Parameters (B) | 7.1 |
| Architecture | Transformer |
| Context Window | 2048 |
| Input Modalities | text |
| Open Source | Yes |
| License | bigscience-bloom-rail-1.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | ~16 GB VRAM for FP16 inference on a single GPU (e.g. RTX 4090, A10, V100 16GB); ~8 GB with 8-bit quantization; finetuned on 64× NVIDIA A100 80GB |
| Benchmark: HumanEval | 8.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |