| from smolagents import Tool | |
| class FrugalAI_methods(Tool): | |
| name = "FrugalAI_methods" | |
| description = "Retrieves methods for model frugalization. It will return ideas to frugalize a code, please use it." | |
| inputs = { | |
| "method": { | |
| "type": "string", | |
| "description": "Always set it to 'Frugal' or it will raise an error." | |
| } | |
| } | |
| output_type = "string" | |
| def forward(self, method): | |
| ideas=[] | |
| ideas.append(pruning()) | |
| ideas.append(quantization()) | |
| return ideas | |
| def pruning(): | |
| """ | |
| Optimizes models by removing unnecessary components, such as certain weights in a neural network. | |
| This function demonstrates how to apply pruning. | |
| """ | |
| code = "model = apply_pruning(model, amount=0.3)" | |
| return ( | |
| f"To apply pruning to a model, use the following code snippet: {code}. " | |
| f"You should adapt it to your actual implementation. In particular, the 'amount' parameter " | |
| f"can be increased or decreased depending on the initial number of weights and the complexity of your use case (minimu value: 0, maximum value: 1). You should give these information to the manager, you can not prune the model yourself." | |
| ) | |
| def quantization(): | |
| """ | |
| Converts high-precision weights into lower-precision one to reduce cost. | |
| """ | |
| code = "model = torch.quantization.quantize_dynamic(model, dtype=torch.qint8)" | |
| return ( | |
| f"To apply quantization to a model, use the following code snippet: {code}. You should give these information to the manager, you can not quantize the model yourself." | |
| ) |