alpindale/WizardLM-2-8x22B
6 derivatives checked
- mradermacher/WizardLM-2-8x22B-i1-GGUF: Quantization
- qwp4w3hyb/Not-WizardLM-2-8x22B-iMat-GGUF: Quantization
- rAIfle/SorcererLM-8x22b-bf16: Full fine-tune
- gghfez/WizardLM-2-22b-RP: MoE built from dense models
- BigHuggyD/BigHuggyD-Grey-WizardLM-2-8x22B: Full fine-tune
- gghfez/experimental_R1-8x22b: Full fine-tune
5 other repos hold byte-for-byte identical weight files.