GreenerPastures/Mike-Hawk-9B

Full fine-tune vs Salesforce/xgen-small-9B-instruct-r. Fine-tune: 96% of the weights changed, across 45 of 45 layers.

Tensors changed: Embeddings 0/1, Norms 48/91, MLP 135/135, Attention 180/180, lm_head 1/1

1 derivatives checked

• mradermacher/Mike-Hawk-9B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse