OpenBuddy/SimpleChat-4B-V1
Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 103/145, MLP 108/108, Attention 144/144
4 derivatives checked
- mradermacher/SimpleChat-4B-V1-i1-GGUF: Quantization
- gabriellarson/SimpleChat-4B-V1-GGUF: Same weights, converted
- prithivMLmods/SimpleChat-4B-V1-f32-GGUF: Same weights, converted
- mradermacher/SimpleChat-4B-V1-GGUF: Same weights, converted