Model Card for FLOPS-Squared/Llama-Baseline-V3-Instruct-B

An extended trained baseline model without using KeystoneFuse data efficient pretraining.

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC)

Downloads last month
4
Safetensors
Model size
252M params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support