emberian/h-05b-replay

Full fine-tune vs tiiuae/Falcon-H1-0.5B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 73/73, MLP 108/108, other 250/252, Attention 144/144

1 derivatives checked

• sizzlebop/h-05b-replay-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse