shuoxing
/

Llama3-8b-Review-lora-lr-1e-5-a-256-alpha-512

Generated from Trainer

8-bit precision

Model card Files Files and versions Community

Llama3-8b-Review-lora-lr-1e-5-a-256-alpha-512

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

shuoxing's picture

Upload folder using huggingface_hub

3010acf verified 12 days ago

checkpoint-491
Upload folder using huggingface_hub 12 days ago
.gitattributes

1.64 kB

Upload folder using huggingface_hub 12 days ago
README.md

3.56 kB

Upload folder using huggingface_hub 12 days ago
adapter_config.json

812 Bytes

Upload folder using huggingface_hub 12 days ago
adapter_model.safetensors

1.34 GB
LFS

Upload folder using huggingface_hub 12 days ago
config.json

1.42 kB

Upload folder using huggingface_hub 12 days ago
special_tokens_map.json

444 Bytes

Upload folder using huggingface_hub 12 days ago
tokenizer.json

17.2 MB
LFS

Upload folder using huggingface_hub 12 days ago
tokenizer_config.json

51.1 kB

Upload folder using huggingface_hub 12 days ago
training_args.bin
Detected Pickle imports (14)
- "axolotl.core.training_args.AxolotlTrainingArguments",
- "torch.bfloat16",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
9.14 kB
LFS

Upload folder using huggingface_hub 12 days ago