GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic
Full fine-tune vs openbmb/MiniCPM5-2B. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 63/85, MLP 126/126, Attention 168/168
5 derivatives checked
- GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF: Same weights, converted
- mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-i1-GGUF: Quantization
- mradermacher/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF: Same weights, converted
- dalatexcoder/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-heretic-ara-strict: Abliterated
- dalatexcoder/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-heretic-ara-lax: Abliterated