aaabiao
/

neo_7B_sft_v0_1_plus-dpo-iter2-beta0_05

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

neo_7B_sft_v0_1_plus-dpo-iter2-beta0_05

1 contributor

History: 9 commits

aaabiao's picture

Update README.md

e558186 verified 7 months ago

runs
Add files using large-upload tool 7 months ago
.gitattributes

1.52 kB

initial commit 7 months ago
README.md

2.02 kB

Update README.md 7 months ago
adapter_config.json

724 Bytes

Add files using large-upload tool 7 months ago
added_tokens.json

104 Bytes

Add files using large-upload tool 7 months ago
all_results.json

885 Bytes

Add files using large-upload tool 7 months ago
config.json

758 Bytes

Add files using large-upload tool 7 months ago
eval_results.json

709 Bytes

Add files using large-upload tool 7 months ago
special_tokens_map.json

658 Bytes

Add files using large-upload tool 7 months ago
tokenization_hkgpt.py

9.63 kB

Add files using large-upload tool 7 months ago
tokenizer.model

1 MB
LFS

Add files using large-upload tool 7 months ago
tokenizer_config.json

3.03 kB

Add files using large-upload tool 7 months ago
train_results.json

196 Bytes

Add files using large-upload tool 7 months ago
trainer_state.json

26.4 kB

Add files using large-upload tool 7 months ago
training_args.bin
Detected Pickle imports (9)
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "alignment.configs.DPOConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.24 kB
LFS

Add files using large-upload tool 7 months ago