sail/Sailor2-L-20B

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

Tensors changed: Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/Sailor2-L-20B-GGUF: Quantization
• sail/Sailor2-L-20B-Chat: Full fine-tune
• sail/Sailor2-L-20B-SFT: Full fine-tune

On the Hub · Downloads on Model Pulse