2048lr/GLM-4.7-Flash-Name-NSFW-GGUF
LoRA-style vs zai-org/GLM-4.7-Flash. 2048lr/GLM-4.7-Flash-Name-NSFW-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate, kv_a_proj_with_mqa, o_proj, q_a_proj, q_b_proj changed, in 47 of 47 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/189, MLP 93/187, Attention 188/188, lm_head 0/1