Abu-Dju/Leanstral-1.5-119B-A6B-GGUF
LoRA-style vs mistralai/Leanstral-1.5-119B-A6B. Abu-Dju/Leanstral-1.5-119B-A6B-GGUF is a GGUF (BF16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of w1, w2, w3, wkv_a_with_mqa, wq_a, wq_b changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/73, other 0/36, Attention 108/108, MLP 108/108