Sakalti/anchobi-4b

Full fine-tune vs sail/Sailor-4B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 51/81, MLP 120/120, Attention 280/280

2 derivatives checked

• mradermacher/anchobi-4b-i1-GGUF: Quantization
• mradermacher/anchobi-4b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse