Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
wangrongsheng
/
Aurora-dpo
like
1
Text Generation
Safetensors
shareAI/ShareGPT-Chinese-English-90k
Chinese
English
doi:10.57967/hf/1635
arxiv:
2312.14557
License:
apache-2.0
Model card
Files
Files and versions
Community
33e1849
Aurora-dpo
/
final_checkpoint
1 contributor
History:
1 commit
wangrongsheng
Upload 12 files
b760542
verified
7 months ago
README.md
1.27 kB
Upload 12 files
7 months ago
adapter_config.json
582 Bytes
Upload 12 files
7 months ago
adapter_model.safetensors
13.6 MB
LFS
Upload 12 files
7 months ago
all_results.json
169 Bytes
Upload 12 files
7 months ago
special_tokens_map.json
437 Bytes
Upload 12 files
7 months ago
tokenizer.model
493 kB
LFS
Upload 12 files
7 months ago
tokenizer_config.json
1.52 kB
Upload 12 files
7 months ago
train_results.json
169 Bytes
Upload 12 files
7 months ago
trainer_log.jsonl
232 kB
Upload 12 files
7 months ago
trainer_state.json
432 kB
Upload 12 files
7 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"torch.device"
,
"transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
How to fix it?
4.86 kB
LFS
Upload 12 files
7 months ago
training_loss.png
39.2 kB
Upload 12 files
7 months ago