🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Merge remote-tracking branch 'origin/expo' into insight-pool-improve
Yizhou Chi3646feb08c92
diff --cc expo/README.mdindex 1d0d8476d,a25f384b6..800afc3cc--- a/expo/README.md+++ b/expo/README.md@@@ -157,35 -135,9 +157,9 @@@ python -u evaluation.py --path "deepseegit clone https://github.com/WecoAI/aideml.git```- Modify `aideml/aide/utils/config.yaml`:-修改 `aideml/aide/utils/config.yaml` 其中的 `step` `k_fold_validation` `code model` `feedback model` 参数如下++Modify `aideml/aide/utils/config.yaml` - change `k_fold_validation`, `code model`, and `feedback model` as follows:```yaml- # path to the task data directory- data_dir: null-- # either provide a path to a plaintext file describing the task- desc_file: null- # or provide the task goal (and optionally evaluation information) as arguments- goal: null- eval: null-- log_dir: logs- workspace_dir: workspaces-- # whether to unzip any archives in the data directory- preprocess_data: True- # whether to copy the data to the workspace directory (otherwise it will be symlinked)- # copying is recommended to prevent the agent from accidentally modifying the original data- copy_data: True-- exp_name: null # a random experiment name will be generated if not provided-- # settings for code execution- exec:- timeout: 3600- agent_file_name: runfile.py- format_tb_ipython: False-# agent hyperparamsagent:# how many improvement iterations to run