unsloth-long-context
Unsloth enables training on extreme context lengths (up to 89K+ on a single 80GB GPU) by utilizing manually derived Triton kernels for RoPE and attention. It optimizes memory usage by a further 30% co
Unsloth enables training on extreme context lengths (up to 89K+ on a single 80GB GPU) by utilizing manually derived Triton kernels for RoPE and attention. It optimizes memory usage by a further 30% co