NJUDeepEngine
/

MeteoRA-llama2-13b

Model card Files Files and versions Community

MeteoRA-llama2-13b / llama2_13b_peft /disfl_qa

1 contributor

History: 1 commit

ParagonLight's picture

upload loras

0a8e533 9 months ago

README.md

2.27 kB

upload loras 9 months ago
adapter_config.json

742 Bytes

upload loras 9 months ago
adapter_model.safetensors

125 MB
LFS

upload loras 9 months ago
all_results.json

361 Bytes

upload loras 9 months ago
eval_results.json

173 Bytes

upload loras 9 months ago
special_tokens_map.json

437 Bytes

upload loras 9 months ago
tokenizer.model

500 kB
LFS

upload loras 9 months ago
tokenizer_config.json

1.41 kB

upload loras 9 months ago
train_results.json

222 Bytes

upload loras 9 months ago
trainer_log.jsonl

46.7 kB

upload loras 9 months ago
trainer_state.json

29.8 kB

upload loras 9 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "torch.device"
How to fix it?
5.18 kB
LFS

upload loras 9 months ago
training_eval_loss.png

40.4 kB

upload loras 9 months ago
training_loss.png

34.5 kB

upload loras 9 months ago