sail/Sailor2-L-20B-Chat

Full fine-tune vs sail/Sailor2-L-20B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 114/129, MLP 192/192, Attention 447/448, lm_head 1/1

1 derivatives checked

• mradermacher/Sailor2-L-20B-Chat-GGUF: Quantization

On the Hub · Downloads on Model Pulse