llama2.go
this is a model for llama2.go project, this project can run meta LLaMA model in less memory like Raspberry Pi.
memory usage
| Model | Precision | Memory | Memory(Cached Params) |
|---|---|---|---|
| 7B | bf16 | 600M+ | 25G+ |
| 13B | bf16 | 1G+ | 43G+ |
| 70B | bf16 | 3G+ | untest |
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.