diff --git a/llmtune/cli/toolkit.py b/llmtune/cli/toolkit.py index ca06680..066b0bd 100644 --- a/llmtune/cli/toolkit.py +++ b/llmtune/cli/toolkit.py @@ -126,7 +126,7 @@ def generate_config(): """ Generate an example `config.yml` file in current directory """ - module_path = Path(llmtune.__file__).parent + module_path = Path(llmtune.__file__) example_config_path = module_path.parent / EXAMPLE_CONFIG_FNAME destination = Path.cwd() shutil.copy(example_config_path, destination) diff --git a/config.yml b/llmtune/config.yml similarity index 91% rename from config.yml rename to llmtune/config.yml index 3bbe1fd..01def93 100644 --- a/config.yml +++ b/llmtune/config.yml @@ -17,15 +17,15 @@ data: prompt_stub: >- # Stub to add for training at the end of prompt, for test set or inference, this is omitted; make sure only one variable is present {output} - test_size: 0.1 # Proportion of test as % of total; if integer then # of samples - train_size: 0.9 # Proportion of train as % of total; if integer then # of samples + test_size: 25 # Proportion of test as % of total; if integer then # of samples + train_size: 500 # Proportion of train as % of total; if integer then # of samples train_test_split_seed: 42 # Model Definition ------------------- model: hf_model_ckpt: "mistralai/Mistral-7B-Instruct-v0.2" torch_dtype: "bfloat16" - attn_implementation: "flash_attention_2" + #attn_implementation: "flash_attention_2" quantize: true bitsandbytes: load_in_4bit: true