From 122cb98adaa0a208363a8dd52c79c5f9372a45ab Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Mon, 3 Nov 2025 12:22:58 +0100 Subject: [PATCH] model-conversion : pass config to from_pretrained This commit modifies the script `run-org-model.py` to ensure that the model configuration is explicitly passed to the `from_pretrained` method when loading the model. It also removes a duplicate configuration loading which was a mistake. The motivation for this change is that enables the config object to be modified and then passed to the model loading function, which can be useful when testing new models. --- .../model-conversion/scripts/causal/run-org-model.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/examples/model-conversion/scripts/causal/run-org-model.py b/examples/model-conversion/scripts/causal/run-org-model.py index 7fb55e9af1f52..85529c612f5b6 100755 --- a/examples/model-conversion/scripts/causal/run-org-model.py +++ b/examples/model-conversion/scripts/causal/run-org-model.py @@ -138,6 +138,9 @@ def fn(_m, input, output): "Model path must be specified either via --model-path argument or MODEL_PATH environment variable" ) + +print("Loading model and tokenizer using AutoTokenizer:", model_path) +tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) print("Model type: ", config.model_type) @@ -147,10 +150,6 @@ def fn(_m, input, output): print("BOS token id: ", config.bos_token_id) print("EOS token id: ", config.eos_token_id) -print("Loading model and tokenizer using AutoTokenizer:", model_path) -tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) -config = AutoConfig.from_pretrained(model_path, trust_remote_code=True) - if unreleased_model_name: model_name_lower = unreleased_model_name.lower() unreleased_module_path = ( @@ -171,7 +170,7 @@ def fn(_m, input, output): exit(1) else: model = AutoModelForCausalLM.from_pretrained( - model_path, device_map="auto", offload_folder="offload", trust_remote_code=True + model_path, device_map="auto", offload_folder="offload", trust_remote_code=True, config=config ) for name, module in model.named_modules():