Chunk-wise backpropagation with a sparse, rescaled variant fine-tunes an 8B model on 16K tokens using a single RTX 3090 GPU.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Training Long-Context LLMs Efficiently via Chunk-wise Optimization
Chunk-wise backpropagation with a sparse, rescaled variant fine-tunes an 8B model on 16K tokens using a single RTX 3090 GPU.