wangzhang/GLM-4.7-Flash-abliteratex
LoRA-style vs zai-org/GLM-4.7-Flash. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate changed, in 37 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/196, MLP 590/2559, Attention 0/240, lm_head 0/1, other 0/2
3 derivatives checked
- mradermacher/GLM-4.7-Flash-abliteratex-i1-GGUF: Quantization
- mradermacher/GLM-4.7-Flash-abliteratex-GGUF: Quantization
- c41n3/GLM-4.7-Flash-abliteratex-Q6_K-GGUF: Quantization