AZERDSQ/ g0-nano-instruct:latest

3 3 days ago

A 62M-parameter GPT trained entirely on a single 8GB-RAM NVIDIA Jetson device, without cloud infrastructure or multi-GPU setups. Both pretraining and instruction fine-tuning occurred within this constraint.

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