GLM-4.7-Flash - Hackdot

Re:GLM-4.7-Flash by twelvechess on Monday January 19, 2026 @10:54AM (#46680358)

Excited to test this out. We need a SOTA 8B model bad though!

[ Parent | on HN ]

Re:GLM-4.7-Flash by cipehr on Monday January 19, 2026 @11:14AM (#46680651)

Is essentialai/rnj-1 not the latest attempt at that?

https://huggingface.co/EssentialAI/rnj-1

[ Parent | on HN ]

Re:GLM-4.7-Flash by metalliqaz on Monday January 19, 2026 @03:54PM (#46684377)

I tried this model and if I recall correctly it was horribly over-trained on Python test questions to the point that if you asked for C code it would say something like "you asked for C code but specified answer must be in Python , so here is the Python ", even though I never once mentioned Python.

[ Parent | on HN ]

Re:GLM-4.7-Flash by piyh on Monday January 19, 2026 @12:33PM (#46681908)

https://docs.mistral.ai/models/ministral-3-8b-25-12

[ Parent | on HN ]

Re:GLM-4.7-Flash by twelvechess on Monday January 19, 2026 @01:22PM (#46682603)

thanks I will try this out

[ Parent | on HN ]