azherali/Riazi-8B-CPT-SFT

Full fine-tune vs unsloth/Qwen3-8B. Fine-tune: 92% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144, lm_head 1/1

1 derivatives checked

• mradermacher/Riazi-8B-CPT-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse