DireDreadlord/Eagle-1-Mini

Partial fine-tune vs tiiuae/Falcon-H1-Tiny-90M-Instruct. Partial change: 82% of the weights changed (attention, mlp, other), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 72/72, other 104/168, Attention 96/96

2 derivatives checked

• mradermacher/Eagle-1-Mini-i1-GGUF: Quantization
• mradermacher/Eagle-1-Mini-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse