zjunlp/OceanGPT-basic-4B-Instruct
Full fine-tune vs Qwen/Qwen3-4B-Instruct-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 142/145, MLP 108/108, Attention 144/144
2 derivatives checked
- mradermacher/OceanGPT-basic-4B-Instruct-i1-GGUF: Quantization
- mradermacher/OceanGPT-basic-4B-Instruct-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.