Novaciano/Infected.Crystal-1B

Full fine-tune vs SyverraStudios/CrystalGPT-1-1b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 79/157, MLP 78/78, Attention 104/104

2 derivatives checked

• mradermacher/Infected.Crystal-1B-i1-GGUF: Quantization
• mradermacher/Infected.Crystal-1B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse