zlab-princeton/Vero-Qwen35-9B-Base

Full fine-tune vs Qwen/Qwen3.5-9B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 4/4, MLP 196/208, Attention 287/332, Norms 160/215

2 derivatives checked

• mradermacher/Vero-Qwen35-9B-Base-i1-GGUF: Quantization
• mradermacher/Vero-Qwen35-9B-Base-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse