diff --git a/examples/scripts/bco.py b/examples/scripts/bco.py index 9f96e3a914c..12a6e85fc08 100644 --- a/examples/scripts/bco.py +++ b/examples/scripts/bco.py @@ -166,10 +166,16 @@ def mean_pooling(model_output, attention_mask): kto_args.gradient_checkpointing_kwargs = {"use_reentrant": True} # Load a pretrained model - model = AutoModelForCausalLM.from_pretrained(model_args.model_name_or_path) - model_ref = AutoModelForCausalLM.from_pretrained(model_args.model_name_or_path) + model = AutoModelForCausalLM.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) + model_ref = AutoModelForCausalLM.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) - tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path) + tokenizer = AutoTokenizer.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token @@ -193,13 +199,15 @@ def format_dataset(example): accelerator = Accelerator() embedding_model = AutoModel.from_pretrained( "nomic-ai/nomic-embed-text-v1.5", - trust_remote_code=True, + trust_remote_code=model_args.trust_remote_code, safe_serialization=True, torch_dtype=torch.bfloat16, device_map="auto", ) embedding_model = accelerator.prepare_model(embedding_model) - embedding_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") + embedding_tokenizer = AutoTokenizer.from_pretrained( + "bert-base-uncased", trust_remote_code=model_args.trust_remote_code + ) embedding_func = partial( embed_prompt, model=embedding_model, diff --git a/examples/scripts/chat.py b/examples/scripts/chat.py index aeaca7cff8d..599cb0ccc19 100644 --- a/examples/scripts/chat.py +++ b/examples/scripts/chat.py @@ -211,19 +211,24 @@ def parse_settings(user_input, current_args, interface): def load_model_and_tokenizer(args): - tokenizer = AutoTokenizer.from_pretrained(args.model_name_or_path, revision=args.model_revision) + tokenizer = AutoTokenizer.from_pretrained( + args.model_name_or_path, + revision=args.model_revision, + trust_remote_code=args.trust_remote_code, + ) torch_dtype = args.torch_dtype if args.torch_dtype in ["auto", None] else getattr(torch, args.torch_dtype) quantization_config = get_quantization_config(args) model_kwargs = dict( revision=args.model_revision, - trust_remote_code=args.trust_remote_code, attn_implementation=args.attn_implementation, torch_dtype=torch_dtype, device_map="auto", quantization_config=quantization_config, ) - model = AutoModelForCausalLM.from_pretrained(args.model_name_or_path, **model_kwargs) + model = AutoModelForCausalLM.from_pretrained( + args.model_name_or_path, trust_remote_code=args.trust_remote_code, **model_kwargs + ) if getattr(model, "hf_device_map", None) is None: model = model.to(args.device) diff --git a/examples/scripts/cpo.py b/examples/scripts/cpo.py index 080e4e6108a..d30429343a8 100644 --- a/examples/scripts/cpo.py +++ b/examples/scripts/cpo.py @@ -76,8 +76,12 @@ class ScriptArguments: ################ # Model & Tokenizer ################ - model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path) - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path) + model = AutoModelForCausalLM.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token diff --git a/examples/scripts/dpo.py b/examples/scripts/dpo.py index 0294932a49a..33e625a7a1a 100644 --- a/examples/scripts/dpo.py +++ b/examples/scripts/dpo.py @@ -106,20 +106,25 @@ quantization_config = get_quantization_config(model_config) model_kwargs = dict( revision=model_config.model_revision, - trust_remote_code=model_config.trust_remote_code, attn_implementation=model_config.attn_implementation, torch_dtype=torch_dtype, use_cache=False if training_args.gradient_checkpointing else True, device_map=get_kbit_device_map() if quantization_config is not None else None, quantization_config=quantization_config, ) - model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path, **model_kwargs) + model = AutoModelForCausalLM.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, **model_kwargs + ) peft_config = get_peft_config(model_config) if peft_config is None: - model_ref = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path, **model_kwargs) + model_ref = AutoModelForCausalLM.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, **model_kwargs + ) else: model_ref = None - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token if tokenizer.chat_template is None: diff --git a/examples/scripts/kto.py b/examples/scripts/kto.py index 26ce812f3a6..74221239d10 100644 --- a/examples/scripts/kto.py +++ b/examples/scripts/kto.py @@ -76,10 +76,16 @@ class ScriptArguments: script_args, kto_args, model_args = parser.parse_args_into_dataclasses() # Load a pretrained model - model = AutoModelForCausalLM.from_pretrained(model_args.model_name_or_path) - model_ref = AutoModelForCausalLM.from_pretrained(model_args.model_name_or_path) + model = AutoModelForCausalLM.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) + model_ref = AutoModelForCausalLM.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) - tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path) + tokenizer = AutoTokenizer.from_pretrained( + model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code + ) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token diff --git a/examples/scripts/orpo.py b/examples/scripts/orpo.py index d0f05f3485d..97118ffd761 100644 --- a/examples/scripts/orpo.py +++ b/examples/scripts/orpo.py @@ -76,8 +76,12 @@ class ScriptArguments: ################ # Model & Tokenizer ################ - model = AutoModelForCausalLM.from_pretrained(model_config.model_name_or_path) - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path) + model = AutoModelForCausalLM.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token diff --git a/examples/scripts/ppo/ppo.py b/examples/scripts/ppo/ppo.py index 417905ff29a..bacb09f77d9 100644 --- a/examples/scripts/ppo/ppo.py +++ b/examples/scripts/ppo/ppo.py @@ -53,15 +53,23 @@ tokenizer = AutoTokenizer.from_pretrained( model_config.model_name_or_path, padding_side="left", - trust_remote_code=True, + trust_remote_code=model_config.trust_remote_code, ) tokenizer.add_special_tokens({"pad_token": "[PAD]"}) if tokenizer.chat_template is None: tokenizer.chat_template = SIMPLE_QUERY_CHAT_TEMPLATE - value_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - reward_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - ref_policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) - policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) + value_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + reward_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + ref_policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) + policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) ################ # Dataset ################ diff --git a/examples/scripts/ppo/ppo_tldr.py b/examples/scripts/ppo/ppo_tldr.py index baa2f404b88..fac09a101da 100644 --- a/examples/scripts/ppo/ppo_tldr.py +++ b/examples/scripts/ppo/ppo_tldr.py @@ -57,15 +57,23 @@ tokenizer = AutoTokenizer.from_pretrained( model_config.model_name_or_path, padding_side="left", - trust_remote_code=True, + trust_remote_code=model_config.trust_remote_code, ) tokenizer.add_special_tokens({"pad_token": "[PAD]"}) if tokenizer.chat_template is None: tokenizer.chat_template = SIMPLE_QUERY_CHAT_TEMPLATE - value_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - reward_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - ref_policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) - policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) + value_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + reward_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + ref_policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) + policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) ################ # Dataset ################ diff --git a/examples/scripts/reward_modeling.py b/examples/scripts/reward_modeling.py index ba3ff73f148..f7c3b013c52 100644 --- a/examples/scripts/reward_modeling.py +++ b/examples/scripts/reward_modeling.py @@ -57,13 +57,14 @@ quantization_config = get_quantization_config(model_config) model_kwargs = dict( revision=model_config.model_revision, - trust_remote_code=model_config.trust_remote_code, device_map=get_kbit_device_map() if quantization_config is not None else None, quantization_config=quantization_config, ) - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path, use_fast=True) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, use_fast=True + ) model = AutoModelForSequenceClassification.from_pretrained( - model_config.model_name_or_path, num_labels=1, **model_kwargs + model_config.model_name_or_path, num_labels=1, trust_remote_code=model_config.trust_remote_code, **model_kwargs ) if model_config.lora_task_type != "SEQ_CLS": diff --git a/examples/scripts/rloo/rloo.py b/examples/scripts/rloo/rloo.py index d0dded14b97..a5342e869d9 100644 --- a/examples/scripts/rloo/rloo.py +++ b/examples/scripts/rloo/rloo.py @@ -55,14 +55,20 @@ tokenizer = AutoTokenizer.from_pretrained( model_config.model_name_or_path, padding_side="left", - trust_remote_code=True, + trust_remote_code=model_config.trust_remote_code, ) tokenizer.add_special_tokens({"pad_token": "[PAD]"}) if tokenizer.chat_template is None: tokenizer.chat_template = SIMPLE_QUERY_CHAT_TEMPLATE - reward_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - ref_policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) - policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) + reward_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + ref_policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) + policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) ################ # Dataset ################ diff --git a/examples/scripts/rloo/rloo_tldr.py b/examples/scripts/rloo/rloo_tldr.py index 02c95e3ea4b..0f8385df2c6 100644 --- a/examples/scripts/rloo/rloo_tldr.py +++ b/examples/scripts/rloo/rloo_tldr.py @@ -59,14 +59,20 @@ tokenizer = AutoTokenizer.from_pretrained( model_config.model_name_or_path, padding_side="left", - trust_remote_code=True, + trust_remote_code=model_config.trust_remote_code, ) tokenizer.add_special_tokens({"pad_token": "[PAD]"}) if tokenizer.chat_template is None: tokenizer.chat_template = SIMPLE_QUERY_CHAT_TEMPLATE - reward_model = AutoModelForSequenceClassification.from_pretrained(config.reward_model_path, num_labels=1) - ref_policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) - policy = AutoModelForCausalLM.from_pretrained(config.sft_model_path) + reward_model = AutoModelForSequenceClassification.from_pretrained( + config.reward_model_path, trust_remote_code=model_config.trust_remote_code, num_labels=1 + ) + ref_policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) + policy = AutoModelForCausalLM.from_pretrained( + config.sft_model_path, trust_remote_code=model_config.trust_remote_code + ) ################ # Dataset ################ diff --git a/examples/scripts/sft.py b/examples/scripts/sft.py index 1df011a4af8..616c1c09631 100644 --- a/examples/scripts/sft.py +++ b/examples/scripts/sft.py @@ -108,7 +108,9 @@ quantization_config=quantization_config, ) training_args.model_init_kwargs = model_kwargs - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path, use_fast=True) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, use_fast=True + ) tokenizer.pad_token = tokenizer.eos_token ################ diff --git a/examples/scripts/vsft_llava.py b/examples/scripts/vsft_llava.py index 32e9e0b804b..7af745afc34 100644 --- a/examples/scripts/vsft_llava.py +++ b/examples/scripts/vsft_llava.py @@ -125,18 +125,23 @@ quantization_config = get_quantization_config(model_config) model_kwargs = dict( revision=model_config.model_revision, - trust_remote_code=model_config.trust_remote_code, attn_implementation=model_config.attn_implementation, torch_dtype=torch_dtype, device_map=get_kbit_device_map() if quantization_config is not None else None, quantization_config=quantization_config, ) - tokenizer = AutoTokenizer.from_pretrained(model_config.model_name_or_path, use_fast=True) + tokenizer = AutoTokenizer.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, use_fast=True + ) tokenizer.chat_template = LLAVA_CHAT_TEMPLATE - processor = AutoProcessor.from_pretrained(model_config.model_name_or_path) + processor = AutoProcessor.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code + ) processor.tokenizer = tokenizer - model = LlavaForConditionalGeneration.from_pretrained(model_config.model_name_or_path, **model_kwargs) + model = LlavaForConditionalGeneration.from_pretrained( + model_config.model_name_or_path, trust_remote_code=model_config.trust_remote_code, **model_kwargs + ) ################ # Create a data collator to encode text and image pairs