YijunLiao/DZ-TDPO-Phi-3.5-mini-instruct
LoRA-style vs microsoft/Phi-3.5-mini-instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_up_proj, o_proj, qkv_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/65, MLP 64/64, Attention 64/64
2 derivatives checked
- mradermacher/DZ-TDPO-Phi-3.5-mini-instruct-i1-GGUF: Quantization
- mradermacher/DZ-TDPO-Phi-3.5-mini-instruct-GGUF: Same weights, converted