virtuous7373/Lambent-Mira-Iris

Full fine-tune vs Lambent/Mira-v1.23-27B-rlvr. Fine-tune: 100% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 4/4, Norms 470/484, MLP 291/294, Attention 462/464, other 1/1

2 derivatives checked

• mradermacher/Lambent-Mira-Iris-i1-GGUF: Quantization (fewer layers)
• mradermacher/Lambent-Mira-Iris-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse