Re:Astra can read and write weights to improve Qwen
by Imnimo on Monday November 02, 2026 @03:58PM
(#50343642)
Under experiment 8 (the one where it fixes performance on GSM8K) it says:
>Then, we allow it to select prompts from the training sets of GSM8K and MATH to perform a budget of forward passes (average batch of 64 sequences, max 512) on, varying the budget across 10, 25 and 50. Again, no training or gradient information is allowed.
No tools or forward passes are allowed