Open zlh1992 opened 1 year ago
By the way is there any 2-bit model weights of llama7b,13b,33b,65b?
You can use load_llama_model_4bit_low_ram and set bits=2. And I haven't seen any 2 bits weight for llama model as well, also curious about it.
By the way is there any 2-bit model weights of llama7b,13b,33b,65b?