WizardLM 13B 1.0 4-bit
From WizardLM: https://huggingface.co/WizardLM/WizardLM-13B-1.0
Folders
ggml: q4_0 and q4_1
gptq: works with Triton and CUDA branches
From WizardLM: https://huggingface.co/WizardLM/WizardLM-13B-1.0
ggml: q4_0 and q4_1
gptq: works with Triton and CUDA branches