Quantizing and running inference on bloom-176B required some changes

[barsuna]

• Most issues are due to fact that embedding layer 250880x14336 is too large to fit into signed integer
• Above affects the main, quantize, and also ggml code
• 2nd issue is that main seems to estimate amount of necessary memory on the low side
• Above is not fixed, i have just added 5GB for weights and doubled the size of context used for model evaluation Being very far away from proficiency in C++, these changes need to be civilized by someone experienced with ggml and c++