Cran-May/PCB-NRSheared-2

Full fine-tune vs AlSamCur123/Mistral-Small3-24B-InstructContinuedFine. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 11/81, MLP 120/120, Attention 160/160, lm_head 1/1

1 derivatives checked

• mradermacher/PCB-NRSheared-2-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse