MotherEarth/MotherEarth-1.12-8B

Full fine-tune vs MotherEarth/MotherEarth-1.0-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 63/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/MotherEarth-1.12-8B-GGUF: Same weights, converted
• MotherEarth/MotherEarth-1.13-8B: Partial fine-tune

On the Hub · Downloads on Model Pulse