mradermacher/es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2_aug-kl0.01-step480-GGUF

Same weights, converted vs sparkle-reasoning/SparkleRL-7B-Stage2-aug. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse