bunnycore/QwQen-3B-LCoT
Full fine-tune vs bunnycore/Qwen2.5-3B-RP-Mix. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 73/73, MLP 108/108, Attention 252/252
5 derivatives checked
- mradermacher/QwQen-3B-LCoT-GGUF: Same weights, converted
- mradermacher/QwQen-3B-LCoT-i1-GGUF: Quantization
- bunnycore/QwQen-3B-LCoT-R1: LoRA-style
- bunnycore/DeepQwen-3B-LCoT-SCE: Full fine-tune
- bunnycore/Qwen2.5-3B-Model-DeepStock-v1: Full fine-tune