(and newest) ] # Quantized GGUF versions generally load faster and run nicely on a laptop with at least 16 GB of RAM gguf_models = ["bling-phi-3-gguf", "bling-stablelm-3b-tool", "dragon-llama-answer-tool", "dragon-yi-answer-tool", "dragon-mistral-answer-tool"] # try model ...
(and newest) ] # Quantized GGUF versions generally load faster and run nicely on a laptop with at least 16 GB of RAM gguf_models = ["bling-phi-3-gguf", "bling-stablelm-3b-tool", "dragon-llama-answer-tool", "dragon-yi-answer-tool", "dragon-mistral-answer-tool"] # try model ...
","base salary":"What is the executive's base salary?","vacation":"How many vacation days will the executive receive?"}# Load the selected model by name that was passed into the functionprint(f"\n> Loading model{model_name}...")prompter=Prompt().load_model(model_name,temperature=0.0...