Aratako/Antler-7B-RP-v2

Partial fine-tune vs Elizezen/Antler-7B. Partial change: 20% of the weights changed (attention, lm_head), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• MCZK/Japanese-Chat-Umievo-itr004-7b-GGUF: Full fine-tune

On the Hub · Downloads on Model Pulse