h34v7/DXP-Zero-V1.2-24b-Small-Instruct

Full fine-tune vs Gryphe/Pantheon-RP-1.8-24b-Small-3.1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

• h34v7/DXP-Zero-V1.2-24b-Small-Instruct-i1-GGUF: Quantization
• h34v7/DXP-Zero-V1.2-24b-Small-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse