dhanesh-hf/Jarvis-Titan-M4-MoE-CSA3

Partial fine-tune vs dhanesh-hf/Jarvis-Titan-V15-MoE-Decoupled. Partial change: 0% of the weights changed (other), in 0 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 0/78, MLP 0/196, Attention 0/217, other 14/63, lm_head 0/1

On the Hub · Downloads on Model Pulse