DevQuasar/arcee-ai.GLM-4-32B-Base-32K-GGUF
Same weights, converted vs arcee-ai/GLM-4-32B-Base-32K. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/245, MLP 0/122, Attention 0/244
Same weights, converted vs arcee-ai/GLM-4-32B-Base-32K. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/245, MLP 0/122, Attention 0/244