| """Offline CPU inference for a complete checkpoint and an explicit label map.""" |
| import argparse |
| import json |
| import os |
| from pathlib import Path |
|
|
|
|
| def main(): |
| parser=argparse.ArgumentParser() |
| parser.add_argument('--model',required=True,help='Existing complete local checkpoint directory; no download is attempted.') |
| parser.add_argument('--input',default=str(Path(__file__).parent/'example_input.json')) |
| parser.add_argument('--labels',default=str(Path(__file__).parent/'labels.json')) |
| parser.add_argument('--validate-only',action='store_true') |
| args=parser.parse_args() |
| for k,v in {'HF_HUB_OFFLINE':'1','TRANSFORMERS_OFFLINE':'1','HF_HUB_DISABLE_TELEMETRY':'1','TOKENIZERS_PARALLELISM':'false','CUDA_VISIBLE_DEVICES':''}.items():os.environ[k]=v |
| model_path=Path(args.model) |
| spec=json.loads(Path(args.labels).read_text()) |
| data=json.loads(Path(args.input).read_text()) |
| for name in ['config.json','model.safetensors','tokenizer.json','tokenizer_config.json']: |
| if not (model_path/name).is_file():raise SystemExit('Required local file absent: '+name) |
| from transformers import AutoConfig,AutoTokenizer |
| config=AutoConfig.from_pretrained(model_path,local_files_only=True,trust_remote_code=False) |
| tokenizer=AutoTokenizer.from_pretrained(model_path,local_files_only=True,trust_remote_code=False) |
| assert config.num_labels==len(spec['labels']), 'Label count does not match checkpoint' |
| enc=tokenizer(data['text'],data.get('text_pair'),truncation=True,max_length=spec['max_length'],return_tensors='pt') |
| if args.validate_only: |
| print(json.dumps({'validation':'passed','labels':config.num_labels,'tokens':int(enc['input_ids'].shape[-1]),'model_loaded':False,'downloads':0})) |
| return |
| import torch |
| from transformers import AutoModelForSequenceClassification |
| torch.set_num_threads(4) |
| model=AutoModelForSequenceClassification.from_pretrained(model_path,local_files_only=True,trust_remote_code=False,dtype=torch.float32,attn_implementation='eager').to('cpu').eval() |
| with torch.inference_mode():logits=model(**enc).logits[0].float() |
| scores=logits.sigmoid() if spec['decision']=='sigmoid_threshold' else logits.softmax(-1) |
| labels=spec['labels'] |
| selected=[labels[i] for i,p in enumerate(scores.tolist()) if p>=spec['threshold']] if spec['decision']=='sigmoid_threshold' else [labels[int(scores.argmax())]] |
| print(json.dumps({'labels':selected,'scores':dict(zip(labels,scores.tolist())),'score_type':spec['decision'],'threshold':spec.get('threshold'),'device':'cpu','logits':logits.tolist()},indent=2)) |
|
|
|
|
| if __name__=='__main__':main() |
|
|
