Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by pama on Monday November 02, 2026 @05:54PM (#50345201)

In fact qwen knows much better math than their final fixed model. The nonthinking qwen 0.6B parameter model had 55.2% correct on math-500 vs their final improved 48.1% fixed-reasoning model, both with a 32k context window. The original qwen reasoning model had 77.6% accuracy on same test, though qwen recommends using a much larger context for these benchmarks. I wonder if their broken baseline run with 7.9% accuracy is a vllm or setup bug, but didnt dig into it any deeper.

Cool work anyways.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by StilesCrisis on Monday November 02, 2026 @07:35PM (#50346381)

Qwen in reasoning mode is ridiculously anxious and ends up going in circles. It's not just math, it's how it behaves in general.

Others have also fine-tuned Qwen to shake this behavior already, so it's honestly not entirely shocking that Astra could too, but I think this is the first time it was done "by hand" and not via fine-tune.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by pama on Monday November 02, 2026 @09:47PM (#50347384)

To be clear, the tuned model here performs worse than the same qwen model performed before RL, which was also not going in circles. It also performs much worse than the RL model that goes in circles. One could argue that the reduction of context may be worth something, but it appears that the final model is worse in all respects than the model at a much earlier stage of training.

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by tesnorindian on Tuesday November 03, 2026 @02:21AM (#50349057)

You can ask Astra to study 2 or more models and ask it to import their layers to the Qwen model. With this will it not gain more than what it learned with RL?

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by big-chungus4 on Tuesday November 03, 2026 @01:55AM (#50348911)

I suspect the model was just hitting 32k context limit because it is trained for reasoning with 256k tokens available, not 32k

[ Parent | on HN ]