wolfram/miquliz-120b-v2.0-GGUF
Full fine-tune (fewer layers) vs 152334H/miqu-1-70b-sf. 152334H/miqu-1-70b-sf matches part of wolfram/miquliz-120b-v2.0-GGUF (723 of its 1263 tensors; the rest of wolfram/miquliz-120b-v2.0-GGUF has no counterpart). On the shared part: wolfram/miquliz-120b-v2.0-GGUF is a GGUF (IQ3_XXS) of different weights. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 120/161, MLP 240/240, Attention 320/320, lm_head 1/1