cerebras/GLM-4.7-REAP-268B-A32B
LoRA-style vs zai-org/GLM-4.7. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 89 of 92 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/369, MLP 1072/1397, Attention 0/644, lm_head 0/1
2 derivatives checked
- mradermacher/GLM-4.7-REAP-268B-A32B-i1-GGUF: Quantization
- mradermacher/GLM-4.7-REAP-268B-A32B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.