GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking
LoRA-style vs openbmb/MiniCPM5-1B. 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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 72/72, Attention 96/96
9 derivatives checked
- GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF: Same weights, converted
- liodon-ai/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-imatrix-GGUF: Quantization
- Nasaawakening/Zoder2.0-1B: LoRA-style
- TenZzz412/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF: Same weights, converted
- Iambackup/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF: Same weights, converted
- nohugs4u69420/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF-clone: Partial fine-tune
- DIRKIEdev/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF: Same weights, converted
- Santost/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF: Same weights, converted
- usermma/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-abliterated: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.