win10/EVA-Instruct-QwQ-32B-Preview

Full fine-tune vs ParasiticRogue/EVA-Instruct-32B-v2. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

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

2 derivatives checked

• mradermacher/EVA-Instruct-QwQ-32B-Preview-i1-GGUF: Quantization
• mradermacher/EVA-Instruct-QwQ-32B-Preview-GGUF: Quantization

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

On the Hub · Downloads on Model Pulse