sky-2002
/

SmolLM2-360M-GRPO-v1

Generated from Trainer

Model card Files Files and versions

SmolLM2-360M-GRPO-v1

716 MB

1 contributor

History: 5 commits

sky-2002's picture

Upload folder using huggingface_hub

6f8c140 verified 9 months ago

checkpoint-100
Upload folder using huggingface_hub 9 months ago
checkpoint-200
Upload folder using huggingface_hub 9 months ago
checkpoint-294
Upload folder using huggingface_hub 9 months ago
.gitattributes

1.52 kB

initial commit 9 months ago
README.md

3.29 kB

Upload folder using huggingface_hub 9 months ago
adapter_config.json

800 Bytes

SmolLM2-360M-GRPO-v1 9 months ago
adapter_model.safetensors

69.5 MB
xet

SmolLM2-360M-GRPO-v1 9 months ago
merges.txt

466 kB

SmolLM2-360M-GRPO-v1 9 months ago
special_tokens_map.json

565 Bytes

SmolLM2-360M-GRPO-v1 9 months ago
tokenizer.json

3.52 MB

SmolLM2-360M-GRPO-v1 9 months ago
tokenizer_config.json

3.65 kB

SmolLM2-360M-GRPO-v1 9 months 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?
5.56 kB
xet

SmolLM2-360M-GRPO-v1 9 months ago
vocab.json

801 kB

SmolLM2-360M-GRPO-v1 9 months ago