Pith. sign in

Title resolution pending

As we can see, for the run without the HT, around 69% of masked elements at iteration 6000 (roughly halfway through training) remain masked at iteration 10000 (towards the end of the training) · 2000

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

cs.LG · 2025-02-07 · conditional · novelty 7.0

A quantization-aware training method with Hadamard normalization and a trust gradient mask trains Llama models stably down to 1-bit weights and activations and makes 4-bit precision Pareto-optimal in accuracy per memory.

citing papers explorer

Showing 1 of 1 citing paper.

  • QuEST: Stable Training of LLMs with 1-Bit Weights and Activations cs.LG · 2025-02-07 · conditional · none · ref 8

    A quantization-aware training method with Hadamard normalization and a trust gradient mask trains Llama models stably down to 1-bit weights and activations and makes 4-bit precision Pareto-optimal in accuracy per memory.