项目地址: https://github.com/lwch/llama2.go
各规格模型所需内存大小：
[td]Model[/td]
[td]Precision[/td]
[td]Memory[/td]
[td]Memory(Cached Params)[/td]
7B
bf16
600M+
25G+
13B
bf16
1G+
43G+
70B
bf16
3G+
untest
模型推理方式:
cat loutre de mer
peppermint => menthe poivrée
plush girafe => girafe peluche
cheese =>
EOF
.... 此处省略一堆中间过程
Translate English to French:
sea otter => loutre de mer
peppermint => menthe poivrée
plush girafe => girafe peluche
cheese => fromage
Traanslate French to English:
lait => milk
推理提速:
[ol]
[/ol]
