AI models
Goat-7B
Parameters
7B
Published
May 23, 2023
Goat-7B is an AI model developed by National University of Singapore (Singapore), first published in May 2023. It works in the language domain, on tasks such as quantitative reasoning.
Epoch AI has no training-compute estimate for this model. The model has 7,000,000,000 parameters. It was trained on roughly 43.7M datapoints. Training ran on NVIDIA A10 PCIe.
Access: Open weights (non-commercial). Its weights are openly available. It is built on top of LLaMA-7B. The reference paper has 107 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- National University of Singapore
- Country of organization
- Singapore
- Domain
- Language
- Task
- Quantitative reasoning
- Parameters
- 7,000,000,000
- Dataset size
- 43.7M
- Training hardware
- NVIDIA A10 PCIe
- Numerical format
- FP16
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Base model
- LLaMA-7B
- Citations
- 107
- Epoch confidence
- Speculative
More from National University of Singapore
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models