alexredna
/

Tukan-1.1B-Chat-v0.6_dpo

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Tukan-1.1B-Chat-v0.6_dpo

1 contributor

History: 2 commits

alexredna's picture

Model save

c686a6b verified about 1 year ago

runs
Model save about 1 year ago
.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

2.93 kB

Model save about 1 year ago
adapter_config.json

590 Bytes

Model save about 1 year ago
adapter_model.safetensors

211 MB
LFS

Model save about 1 year ago
all_results.json

744 Bytes

Model save about 1 year ago
eval_results.json

571 Bytes

Model save about 1 year ago
special_tokens_map.json

551 Bytes

Model save about 1 year ago
tokenizer.json

1.84 MB

Model save about 1 year ago
tokenizer_config.json

1.38 kB

Model save about 1 year ago
train_results.json

194 Bytes

Model save about 1 year ago
trainer_state.json

11.6 kB

Model save about 1 year ago
training_args.bin
Detected Pickle imports (8)
- "alignment.configs.DPOConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
4.92 kB
LFS

Model save about 1 year ago