XGenerationLab/XiYanSQL-QwenCoder-7B-2504

Partial fine-tune vs XGenerationLab/XiYanSQL-QwenCoder-7B-2502. Partial change: 86% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 41/57, MLP 84/84, Attention 196/196, lm_head 0/1

1 derivatives checked

• mradermacher/XiYanSQL-QwenCoder-7B-2504-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse