NJUDeepEngine
/

MeteoRA-llama3-8b

Model card Files Files and versions

MeteoRA-llama3-8b / llama3_8b_peft /winowhy

93.2 MB

1 contributor

History: 1 commit

ParagonLight's picture

update lora adapters

90d0181 over 1 year ago

README.md

1.79 kB

update lora adapters over 1 year ago
adapter_config.json

738 Bytes

update lora adapters over 1 year ago
adapter_model.safetensors

83.9 MB
xet

update lora adapters over 1 year ago
all_results.json

350 Bytes

update lora adapters over 1 year ago
eval_results.json

164 Bytes

update lora adapters over 1 year ago
special_tokens_map.json

335 Bytes

update lora adapters over 1 year ago
tokenizer.json

9.08 MB

update lora adapters over 1 year ago
tokenizer_config.json

51 kB

update lora adapters over 1 year ago
train_results.json

207 Bytes

update lora adapters over 1 year ago
trainer_log.jsonl

36.3 kB

update lora adapters over 1 year ago
trainer_state.json

23 kB

update lora adapters over 1 year ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "torch.device",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState"
How to fix it?
5.18 kB
xet

update lora adapters over 1 year ago
training_eval_loss.png

42.8 kB

update lora adapters over 1 year ago
training_loss.png

31.9 kB

update lora adapters over 1 year ago