ChosenQ
/

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

1 contributor

History: 5 commits

This model has 1 file scanned as unsafe.

ChosenQ's picture

Training in progress, step 34

d1c750a verified 17 days ago

.gitattributes

1.57 kB

Training in progress, step 100 18 days ago
config.json

768 Bytes

Training in progress, step 100 18 days ago
model.safetensors

3.55 GB
LFS

Training in progress, step 34 17 days ago
special_tokens_map.json

485 Bytes

Training in progress, step 100 18 days ago
tokenizer.json

11.4 MB
LFS

Training in progress, step 100 18 days ago
tokenizer_config.json

6.77 kB

Training in progress, step 34 17 days ago
training_args.bin
Detected Pickle imports (15)
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "torch.bfloat16",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "open_r1.configs.GRPOConfig",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "__builtin__.getattr",
- "transformers.training_args.OptimizerNames",
- "torch.device"
How to fix it?
8.12 kB
LFS

Training in progress, step 34 17 days ago