Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dian1414
/
Qwen3-1.7B-GRPO-zero3
like
0
Transformers
Safetensors
simplescaling/s1K_tokenized
Generated from Trainer
trl
grpo
arxiv:
2402.03300
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
main
Qwen3-1.7B-GRPO-zero3
6.94 GB
1 contributor
History:
3 commits
This model has 16 files scanned as unsafe.
Show
files
dian1414
End of training
c284471
verified
6 months ago
global_step125
End of training
6 months ago
global_step142
End of training
6 months ago
.gitattributes
Safe
1.57 kB
End of training
6 months ago
README.md
2.37 kB
End of training
6 months ago
adapter_config.json
Safe
710 Bytes
End of training
6 months ago
adapter_model.safetensors
Safe
40 Bytes
xet
End of training
6 months ago
added_tokens.json
Safe
707 Bytes
End of training
6 months ago
latest
Safe
14 Bytes
End of training
6 months ago
merges.txt
Safe
1.67 MB
End of training
6 months ago
special_tokens_map.json
Safe
613 Bytes
End of training
6 months ago
tokenizer.json
Safe
11.4 MB
xet
End of training
6 months ago
tokenizer_config.json
Safe
9.73 kB
End of training
6 months ago
training_args.bin
Unsafe
pickle
Detected Pickle imports (15)
"__builtin__.getattr"
,
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SaveStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.IntervalStrategy"
,
"torch.bfloat16"
,
"trl.trainer.grpo_config.GRPOConfig"
,
"accelerate.state.PartialState"
,
"transformers.training_args.OptimizerNames"
How to fix it?
7.8 kB
xet
End of training
6 months ago
vocab.json
Safe
2.78 MB
End of training
6 months ago
zero_to_fp32.py
Safe
33.3 kB
End of training
6 months ago