ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support mllm hf inference

Browse Source 
Former-commit-id: 2c7c01282acd7ddabbb17ce3246b8dae4bc4b8cf
This commit is contained in:
hiyouga
2024-04-26 05:34:58 +08:00
parent 10a6c395bb
commit 23b881bff1
23 changed files with 128 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llmtuner/train/utils.py
View File

@@ -91,7 +91,7 @@ def create_ref_model(
)
ref_model_args = ModelArguments(**ref_model_args_dict)
ref_finetuning_args = FinetuningArguments(finetuning_type="lora")
tokenizer = load_tokenizer(ref_model_args)
tokenizer = load_tokenizer(ref_model_args)["tokenizer"]
ref_model = load_model(
tokenizer, ref_model_args, ref_finetuning_args, is_trainable=False, add_valuehead=add_valuehead
)
@@ -100,7 +100,7 @@ def create_ref_model(
if finetuning_args.finetuning_type == "lora":
ref_model = None
else:
tokenizer = load_tokenizer(model_args)
tokenizer = load_tokenizer(model_args)["tokenizer"]
ref_model = load_model(
tokenizer, model_args, finetuning_args, is_trainable=False, add_valuehead=add_valuehead
)
@@ -147,7 +147,7 @@ def create_reward_model(
)
reward_model_args = ModelArguments(**reward_model_args_dict)
reward_finetuning_args = FinetuningArguments(finetuning_type="lora")
tokenizer = load_tokenizer(reward_model_args)
tokenizer = load_tokenizer(reward_model_args)["tokenizer"]
reward_model = load_model(
tokenizer, reward_model_args, reward_finetuning_args, is_trainable=False, add_valuehead=True
)