cerebras/GLM-4.6-REAP-252B-A32B
LoRA-style (fewer layers) vs zai-org/GLM-4.6. cerebras/GLM-4.6-REAP-252B-A32B matches part of zai-org/GLM-4.6 (31195 of its 44689 tensors; the rest of zai-org/GLM-4.6 has no counterpart). On the shared part: 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 1033/1331, Attention 0/644, lm_head 0/1