mradermacher/AdaTooler-V-SFT-model-GGUF

Full fine-tune (fewer layers) vs AdaTooler-V/AdaTooler-V-SFT-model. mradermacher/AdaTooler-V-SFT-model-GGUF matches part of AdaTooler-V/AdaTooler-V-SFT-model (339 of its 729 tensors; the rest of AdaTooler-V/AdaTooler-V-SFT-model has no counterpart). On the shared part: mradermacher/AdaTooler-V-SFT-model-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1

On the Hub · Downloads on Model Pulse