veyra-ai/veyra2-30m-base-2b-tokens
Text Generation • 34.6M • Updated • 369 • 1
Veyra2
The second generation of Veyra, these models are meant for local CPU inference.
-
-
veyra-ai/veyra2-30m-base-2b-tokens-gguf
Text Generation • 34.6M • Updated • 322 -
veyra-ai/veyra2-30m-base-2b-tokens-onnx-int8
Text Generation • Updated • 63 -
veyra-ai/veyra2-15m-base-1b-tokens
Text Generation • 14.7M • Updated • 216 -
veyra-ai/veyra2-30m-instruct-early
Text Generation • 34.6M • Updated • 31 -
veyra-ai/veyra2-30m-instruct-early-onnx-int8
Text Generation • 34.6M • Updated • 4