mradermacher/TigerLLM-9B-it-GGUF
Full fine-tune (fewer layers) vs md-nishat-008/TigerLLM-9B-it. mradermacher/TigerLLM-9B-it-GGUF matches part of md-nishat-008/TigerLLM-9B-it (626 of its 1065 tensors; the rest of md-nishat-008/TigerLLM-9B-it has no counterpart). On the shared part: mradermacher/TigerLLM-9B-it-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 0/289, MLP 144/144, Attention 192/192