QUEN 3.5 0.8b
A small language model in Alibaba's Qwen series with approximately 0.8B parameters, suited to lightweight local inference scenarios.
Timeline (last 90 days)
By editing an extremely small portion of the weights, Astra raised QUEN 3.5 0.8b's solve rate on math problems from roughly 1 correct out of every 13 problems to close to half.
In the QUEN 3.5 0.8b case, Astra broke a reasoning loop by editing an extremely small proportion of the weights; this is an application of weight editing, which, unlike fine-tuning, does not rely on gradient descent but directly modifies parameter values.
All Facts (2)
By editing an extremely small portion of the weights, Astra raised QUEN 3.5 0.8b's solve rate on math problems from roughly 1 correct out of every 13 problems to close to half.
50%UnverifiedIn the QUEN 3.5 0.8b case, Astra broke a reasoning loop by editing an extremely small proportion of the weights; this is an application of weight editing, which, unlike fine-tuning, does not rely on gradient descent but directly modifies parameter values.
50%