anthracite-org/magnum-v2-4b

Full fine-tune vs nvidia/Llama-3.1-Minitron-4B-Width-Base. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

4 derivatives checked

• bartowski/magnum-v2-4b-GGUF: Same weights, converted
• mradermacher/magnum-v2-4b-i1-GGUF: Quantization
• anthracite-org/magnum-v2-4b-gguf: Quantization
• mradermacher/magnum-v2-4b-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse