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

2
src/llmtuner/eval/evaluator.py
View File

@@ -21,7 +21,7 @@ from .template import get_eval_template
class Evaluator:
def __init__(self, args: Optional[Dict[str, Any]] = None) -> None:
self.model_args, self.data_args, self.eval_args, finetuning_args = get_eval_args(args)
self.tokenizer = load_tokenizer(self.model_args)
self.tokenizer = load_tokenizer(self.model_args)["tokenizer"]
self.tokenizer.padding_side = "right" # avoid overflow issue in batched inference for llama2
self.template = get_template_and_fix_tokenizer(self.tokenizer, self.data_args.template)
self.model = load_model(self.tokenizer, self.model_args, finetuning_args)