AZERDSQ/ g1-nano-instruct:latest

6 hours ago

A 60M-parameter GPT pretrained and instruction-tuned on a single 8GB-RAM NVIDIA Jetson, offering a native 2048-token context and real multi-turn conversation support.

... /
template
ffc37f014cf7 · 41B
<|user|>{{ .Prompt }}<|end|><|assistant|>