clintlord/phi4_sql_finetuned
LoRA-style vs microsoft/Phi-4-mini-instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of qkv_proj changed, in 16 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 16/64
2 derivatives checked
- mradermacher/phi4_sql_finetuned-i1-GGUF: Quantization
- mradermacher/phi4_sql_finetuned-GGUF: Same weights, converted