NLG_Project / grpo-qwen2.5-3b

6.18 GB

Ctrl+K

Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps)

79138e4 verified about 1 month ago

chat_template.jinja

2.51 kB
Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
config.json

1.55 kB
Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
generation_config.json

216 Bytes
Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
model.safetensors

6.17 GB
xet

Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
tokenizer.json

11.4 MB
xet

Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
tokenizer_config.json

664 Bytes
Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
6.9 kB
xet

Add GRPO Qwen2.5-3B full model (DINOv2 reward, 1701 steps) about 1 month ago