mradermacher/ui-tars-1.5-7b-idm-full-sft-i1-GGUF
Full fine-tune (fewer layers) vs aylinakkus/ui-tars-1.5-7b-idm-full-sft. mradermacher/ui-tars-1.5-7b-idm-full-sft-i1-GGUF matches part of aylinakkus/ui-tars-1.5-7b-idm-full-sft (339 of its 729 tensors; the rest of aylinakkus/ui-tars-1.5-7b-idm-full-sft has no counterpart). On the shared part: mradermacher/ui-tars-1.5-7b-idm-full-sft-i1-GGUF is a GGUF (Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 53/57, MLP 84/84, Attention 196/196, lm_head 1/1