grimjim/kukulemon-32K-7B
Full fine-tune vs grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
2 derivatives checked
- grimjim/kukulemon-32K-7B-GGUF: Quantization
- grimjim/kukulemon-v3-soul_mix-32k-7B: Partial fine-tune