virtuous7373/Lambent-Mira-Calliope

Full fine-tune vs Lambent/Mira-v1.21-27B-rlvr. Fine-tune: 98% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 1/4, Norms 234/484, MLP 186/294, Attention 248/464, other 1/1

2 derivatives checked

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

On the Hub · Downloads on Model Pulse