TheBigBlender/Daisuke-GGUF

Full fine-tune (fewer layers) vs PygmalionAI/pygmalion-2-13b. PygmalionAI/pygmalion-2-13b matches part of TheBigBlender/Daisuke-GGUF (363 of its 561 tensors; the rest of TheBigBlender/Daisuke-GGUF has no counterpart). On the shared part: TheBigBlender/Daisuke-GGUF is a GGUF (F16) of different weights. Fine-tune: 99% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 78/81, MLP 120/120, Attention 160/160, lm_head 0/1

On the Hub · Downloads on Model Pulse