grimjim/kukulemon-spiked-9B

Partial fine-tune vs grimjim/kukulemon-7B. Partial change: 60% of the weights changed (attention, mlp, norms), in 20 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 40/65, MLP 60/96, Attention 80/128, lm_head 0/1

2 derivatives checked

• grimjim/kukulemon-spiked-9B-GGUF: Quantization
• mradermacher/kukulemon-spiked-9B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse