OliviaRossi/TripleTrouble-V3
Partial fine-tune vs Kwaipilot/KAT-Coder-V2.5-Dev. Partial change: 49% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 1/1, MLP 200/2587, lm_head 1/1, Norms 105/131, Attention 247/280
3 derivatives checked
- mradermacher/TripleTrouble-V3-i1-GGUF: Quantization
- mradermacher/TripleTrouble-V3-GGUF: Quantization
- OliviaRossi/TripleTrouble-V3-Q5_K_M-GGUF: Quantization