whcl412/LycheeAI-coder-2b-II-pro-f16
LoRA-style vs openbmb/MiniCPM5-2B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 16 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/85, MLP 48/126, Attention 64/168
2 derivatives checked
- mradermacher/LycheeAI-coder-2b-II-pro-f16-i1-GGUF: Quantization
- mradermacher/LycheeAI-coder-2b-II-pro-f16-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.