Guilherme34/Firefly-V2

Full fine-tune vs Guilherme34/Firefly. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112

3 derivatives checked

• mradermacher/Firefly-V2-i1-GGUF: Quantization
• mradermacher/Firefly-V2-GGUF: Same weights, converted
• Guilherme34/Firefly-V2.5: LoRA-style

On the Hub · Downloads on Model Pulse