ClaudioItaly/Albacus

Partial fine-tune vs ClaudioItaly/Evolutionstory-7B-v2.2. Partial change: 84% of the weights changed (attention, mlp, norms), in 28 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 56/65, MLP 84/96, Attention 112/128

2 derivatives checked

• mradermacher/Albacus-i1-GGUF: Quantization
• mradermacher/Albacus-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse