Delta-Vector/GLM-4-32B-Tulu-Instruct
Full fine-tune vs arcee-ai/GLM-4-32B-Base-32K. Fine-tune: 100% of the weights changed, across 61 of 61 layers.
Tensors changed: Norms 104/245, MLP 122/122, Attention 244/244
5 derivatives checked
- mradermacher/GLM-Tulu-ChatML-i1-GGUF: Quantization
- mradermacher/GLM-4-32B-Tulu-Instruct-i1-GGUF: Quantization
- mradermacher/GLM-4-32B-Tulu-Instruct-GGUF: Quantization
- mradermacher/GLM-Tulu-ChatML-GGUF: Quantization
- Delta-Vector/Austral-GLM4-SFT: LoRA-style
1 other repos hold byte-for-byte identical weight files.