XGenerationLab/XiYanSQL-QwenCoder-3B-2504

Partial fine-tune vs XGenerationLab/XiYanSQL-QwenCoder-3B-2502. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 44/73, MLP 108/108, Attention 247/252

1 derivatives checked

• mradermacher/XiYanSQL-QwenCoder-3B-2504-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse