FourOhFour/Vapor_7B
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 49/57, MLP 84/84, Attention 195/196, lm_head 1/1
5 derivatives checked
- mradermacher/Vapor_7B-i1-GGUF: Quantization
- QuantFactory/Qwen2.5-7B-TitanFusion-GGUF: Full fine-tune
- mradermacher/Vapor_7B-GGUF: Same weights, converted
- FourOhFour/Smoke_7B: Full fine-tune
- bunnycore/Qwen2.5-7B-TitanFusion: Full fine-tune