Gueule-d-ange
/

glm-ocr-quotation-extraction

Model card Files Files and versions

glm-ocr-quotation-extraction

2.22 GB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

Gueule-d-ange's picture

feat: retrain with balanced negatives (47.5% pos / 52.5% neg) - train_loss=0.061 eval_loss=0.058

e2308af verified 9 days ago

.gitattributes

1.52 kB
initial commit about 1 month ago
chat_template.jinja

4.61 kB
Upload fine-tuned GLM-OCR quotation extraction model about 1 month ago
config.json

1.72 kB
Add LoRA fine-tuned GLM-OCR for quotation extraction (10 epochs) 13 days ago
generation_config.json

161 Bytes
Add LoRA fine-tuned GLM-OCR for quotation extraction (10 epochs) 13 days ago
model.safetensors

2.21 GB
xet

feat: retrain with balanced negatives (47.5% pos / 52.5% neg) - train_loss=0.061 eval_loss=0.058 9 days ago
processor_config.json

1.33 kB
Add LoRA fine-tuned GLM-OCR for quotation extraction (10 epochs) 13 days ago
tokenizer.json

6.84 MB
Upload fine-tuned GLM-OCR quotation extraction model about 1 month ago
tokenizer_config.json

1.07 kB
Add LoRA fine-tuned GLM-OCR for quotation extraction (10 epochs) 13 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "transformers.training_args.TrainingArguments"
How to fix it?
4.98 kB
xet

Upload fine-tuned GLM-OCR: 10 epochs, 2901 tasks (quotation + COCO negatives), eval_loss=0.1018 21 days ago