Extreme low-bit quantization with HQQ+ (HQQ + LoRA adapter)
-
mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq
Text Generation • Updated • 50 • 73 -
mobiuslabsgmbh/Llama-2-7b-chat-hf_2bitgs8_hqq
Text Generation • Updated • 33 • 34 -
mobiuslabsgmbh/Llama-2-7b-chat-hf_4bitnogs_hqq
Text Generation • Updated • 9 • 1 -
mobiuslabsgmbh/Llama-3-8b-instruct_2bitgs64_hqq
Text Generation • Updated • 16 • 10