mazesmazes
/

tiny-turn

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

273 MB

Ctrl+K

Ctrl+K

1 contributor

History: 21 commits

mazesmazes's picture

Re-tune threshold via observed-score sweep (was 0.01; now 1.18e-6; TPR 0.25 -> 0.95)

4bc5169 verified 5 days ago

.gitattributes

1.52 kB
initial commit 5 days ago
README.md

2.37 kB
Model save 5 days ago
chat_template.jinja

368 Bytes
Training in progress, step 1000 5 days ago
config.json

906 Bytes
Training in progress, step 1000 5 days ago
generation_config.json

141 Bytes
Training in progress, step 1000 5 days ago
model.safetensors

269 MB
xet

Model save 5 days ago
tiny_turn_meta.json

37 Bytes
Re-tune threshold via observed-score sweep (was 0.01; now 1.18e-6; TPR 0.25 -> 0.95) 5 days ago
tokenizer.json

3.52 MB
Training in progress, step 1000 5 days ago
tokenizer_config.json

424 Bytes
Training in progress, step 1000 5 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.2 kB
xet

Training in progress, step 1000 5 days ago