GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-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
7 derivatives checked
- GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF: Same weights, converted
- saidutta69/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic: Abliterated
- chiakelvin/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-heretic: Abliterated
- mlx-community/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-OptiQ-4bit: Quantization
- kaufkino/MiniCPM5-1B-Fable5-Thinking-T-Wix-ru: LoRA-style
- liodon-ai/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-imatrix-GGUF: Quantization
- droplychee-core/droplychee-small-1b-v1: LoRA-style