crumb
/

768d-init

Text Generation

Model card Files Files and versions

768d-init / README.md

crumb's picture

Update README.md

07f04b1 about 2 years ago

|

history blame contribute delete

169 Bytes

	`31,870,464` non-embedding params, `38,598,913` embedding params, `70,469,377` total.
	```
	"n_embd": 768
	"n_head": 6
	"n_inner": 1920
	"n_layer": 6
	"n_positions": 4096
	```