bzhang0426
/

LLaMA3-70B-qlora-bnb-A61K

Generated from Trainer

4-bit precision

Model card Files Files and versions Community

LLaMA3-70B-qlora-bnb-A61K

1 contributor

History: 2 commits

bzhang0426's picture

Upload 15 files

c0abf45 verified 7 months ago

.gitattributes

1.52 kB

initial commit 7 months ago
README.md

1.84 kB

Upload 15 files 7 months ago
adapter_config.json

666 Bytes

Upload 15 files 7 months ago
adapter_model.safetensors

65.6 MB
LFS

Upload 15 files 7 months ago
all_results.json

366 Bytes

Upload 15 files 7 months ago
config.json

1.19 kB

Upload 15 files 7 months ago
eval_results.json

177 Bytes

Upload 15 files 7 months ago
special_tokens_map.json

464 Bytes

Upload 15 files 7 months ago
tokenizer.json

9.09 MB

Upload 15 files 7 months ago
tokenizer_config.json

51.1 kB

Upload 15 files 7 months ago
train_results.json

224 Bytes

Upload 15 files 7 months ago
trainer_log.jsonl

19 kB

Upload 15 files 7 months ago
trainer_state.json

12.4 kB

Upload 15 files 7 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
How to fix it?
5.18 kB
LFS

Upload 15 files 7 months ago
training_eval_loss.png

42.7 kB

Upload 15 files 7 months ago
training_loss.png

31.1 kB

Upload 15 files 7 months ago