choonok/VetJarvis-1.1-4B-Instruct

Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 4/5, MLP 149/199, Attention 267/324, Norms 111/209, other 1/1

3 derivatives checked

• mradermacher/VetJarvis-1.1-4B-Instruct-i1-GGUF: Quantization
• mradermacher/VetJarvis-1.1-4B-Instruct-GGUF: Same weights, converted
• choonok/VetJarvis-1.1-4B-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse