niklasm222
/

Qwen-0.5B-GRPO

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

1 contributor

History: 2 commits

niklasm222's picture

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog

e40347b verified 6 days ago

.gitattributes

1.57 kB

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
README.md

2.29 kB

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
adapter_config.json

806 Bytes

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
adapter_model.safetensors

45.1 MB
LFS

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
special_tokens_map.json

325 Bytes

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
tokenizer.json

17.2 MB
LFS

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
tokenizer_config.json

54.6 kB

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "trl.trainer.grpo_config.GRPOConfig",
- "accelerate.state.PartialState"
How to fix it?
5.82 kB
LFS

niklasm222/llama-3.2-1b-it-GRPO-gsm8k-prolog 6 days ago