changjiakawhi
/

Qwen2.5-1.5B-Open-R1-Distill-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Qwen2.5-1.5B-Open-R1-Distill-GRPO

1 contributor

History: 3 commits

This model has 1 file scanned as unsafe.

changjiakawhi's picture

End of training

2cbad4a verified 1 day ago

.gitattributes

1.57 kB

Model save 1 day ago
README.md

2.36 kB

End of training 1 day ago
added_tokens.json

605 Bytes

Model save 1 day ago
all_results.json

367 Bytes

End of training 1 day ago
config.json

774 Bytes

End of training 1 day ago
eval_results.json

168 Bytes

End of training 1 day ago
generation_config.json

247 Bytes

Model save 1 day ago
merges.txt

1.67 MB

Model save 1 day ago
model.safetensors

3.55 GB
LFS

Model save 1 day ago
special_tokens_map.json

610 Bytes

Model save 1 day ago
tokenizer.json

11.4 MB
LFS

Model save 1 day ago
tokenizer_config.json

7.36 kB

Model save 1 day ago
train_results.json

201 Bytes

Model save 1 day ago
trainer_state.json

25.7 kB

Model save 1 day ago
training_args.bin
Detected Pickle imports (15)
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "__builtin__.getattr",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "open_r1.configs.GRPOConfig",
- "transformers.trainer_utils.SchedulerType",
- "torch.bfloat16",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
7.67 kB
LFS

Model save 1 day ago
vocab.json

2.78 MB

Model save 1 day ago