bunnycore/Qwen2.5-3B-RP-Mix
Partial fine-tune vs Qwen/Qwen2.5-3B-Instruct. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 3/73, MLP 108/108, Attention 145/252
6 derivatives checked
- mradermacher/Qwen2.5-3B-RP-Mix-i1-GGUF: Quantization
- mradermacher/Qwen2.5-3B-RP-Mix-GGUF: Same weights, converted
- MaziyarPanahi/Qwen2.5-3B-RP-Mix-GGUF: Same weights, converted
- AndriLawrence/Qwen-3B-Intent-Microplan-v1: LoRA-style
- bunnycore/QwQen-3B-LCoT: Full fine-tune
- bunnycore/Qwen2.5-3B-Smart: LoRA-style
1 other repos hold byte-for-byte identical weight files.