synthetic-code-training/hybrid_play_32b

Full fine-tune vs StephenZhu/SWE-Play-32B-mix. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 126/129, MLP 192/192, Attention 448/448, lm_head 1/1

2 derivatives checked

• mradermacher/hybrid_play_32b-i1-GGUF: Quantization
• mradermacher/hybrid_play_32b-GGUF: Quantization

On the Hub · Downloads on Model Pulse