arcee-ai/GLM-4-32B-Base-32K
Full fine-tune vs zai-org/GLM-4-32B-Base-0414. Fine-tune: 100% of the weights changed, across 61 of 61 layers.
Tensors changed: Norms 176/245, MLP 122/122, Attention 244/244
6 derivatives checked
- bartowski/arcee-ai_GLM-4-32B-Base-32K-GGUF: Same weights, converted
- mradermacher/GLM-4-32B-Base-32K-i1-GGUF: Quantization
- DevQuasar/arcee-ai.GLM-4-32B-Base-32K-GGUF: Same weights, converted
- mradermacher/GLM-4-32B-Base-32K-GGUF: Quantization
- ConicCat/GL-Marvin-32k-32B: Full fine-tune
- Delta-Vector/GLM-4-32B-Tulu-Instruct: Full fine-tune