beyoru/Orbit

Full fine-tune vs Qwen/Qwen3.5-35B-A3B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 4/4, Attention 380/388, MLP 312/312, Norms 241/241

1 derivatives checked

• mradermacher/Orbit-GGUF: Quantization

On the Hub · Downloads on Model Pulse