MotherEarth/MotherEarth-1.13-8B

Partial fine-tune vs MotherEarth/MotherEarth-1.12-8B. Partial change: 81% of the weights changed (attention, mlp, norms), in 30 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 60/65, MLP 90/96, Attention 120/128

2 derivatives checked

• mradermacher/MotherEarth-1.13-8B-GGUF: Same weights, converted
• MotherEarth/MotherEarth-1.14-8B: Partial fine-tune

On the Hub · Downloads on Model Pulse