mainguyen9/vietlegal-harrier-0.6b

Partial fine-tune vs microsoft/harrier-oss-v1-0.6b. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 98/113, MLP 84/84, Attention 112/112

2 derivatives checked

• darklethelong/vnlegal-lal: LoRA-style
• mradermacher/vietlegal-harrier-0.6b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse