GPT-Neo models
3 GPT-Neo models on Hugging Face, from 150M to 2.7B parameters. At the precision each one is published in, the smallest needs about 0.7 GB of VRAM (gpt-neo-125m, cheapest live fit: V100) and the largest about 12.2 GB (gpt-neo-2.7B, cheapest live fit: V100). The cheapest way to run gpt-neo-125m is $0.088/hr.
GPT-Neo models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gpt-neo-125m | 150M | F32 | 0.7 GB | V100 | $0.088/hr |
| gpt-neo-1.3B | 1.4B | F32 | 6.1 GB | V100 | $0.088/hr |
| gpt-neo-2.7B | 2.7B | F32 | 12.2 GB | V100 | $0.088/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from EleutherAI
- Pythia (15 models)
