Delta-Vector/Hamanasu-QwQ-V2-RP

Full fine-tune vs Delta-Vector/Hamanasu-QwQ-V1.5-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/Hamanasu-QwQ-V2-RP-i1-GGUF: Quantization
• mradermacher/Hamanasu-QwQ-V2-RP-GGUF: Quantization
• Delta-Vector/Hamanasu-Magnum-QwQ-32B: Full fine-tune

On the Hub · Downloads on Model Pulse