ReDiX/Legal-Embedding-ita-0.6B

Partial fine-tune vs Qwen/Qwen3-Embedding-0.6B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 47/113, MLP 84/84, Attention 111/112

1 derivatives checked

• mradermacher/Legal-Embedding-ita-0.6B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse