mlabonne/Zebrafish-7B

Full fine-tune vs liminerity/M7-7b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Attention 128/128, Norms 18/65, Embeddings 1/1, lm_head 1/1

1 derivatives checked

• featherless-ai-quants/mlabonne-Zebrafish-7B-GGUF: Quantization

On the Hub · Downloads on Model Pulse