prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF
Full fine-tune (fewer layers) vs prithivMLmods/Gliese-CUA-Tool-Call-8B. prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF matches part of prithivMLmods/Gliese-CUA-Tool-Call-8B (339 of its 729 tensors; the rest of prithivMLmods/Gliese-CUA-Tool-Call-8B has no counterpart). On the shared part: prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196