theostos/qwen-3.5-babel-27b-sft

Full fine-tune vs Qwen/Qwen3.5-27B. Fine-tune: 95% of the weights changed, across 64 of 64 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, MLP 192/192, Attention 353/448, Norms 116/209

1 derivatives checked

• mradermacher/qwen-3.5-babel-27b-sft-GGUF: Quantization

On the Hub · Downloads on Model Pulse