ArliAI/GLM-4.6-REAP-268B-A32B-Derestricted
LoRA-style vs cerebras/GLM-4.6-REAP-268B-A32B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate, o_proj changed, in 20 of 92 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/369, MLP 155/1985, Attention 20/644, lm_head 0/1
1 derivatives checked
- mradermacher/GLM-4.6-REAP-268B-A32B-Derestricted-i1-GGUF: Quantization