nabeelshan
/

rlhf-gpt2-pipeline

Text Generation

reinforcement-learning

instruction-tuning

Model card Files Files and versions

rlhf-gpt2-pipeline / sft_full_final

501 MB

2 contributors

History: 1 commit

Nabeel Shan

Added SFT, Reward Model, and PPO-Aligned Model

46724ea 3 months ago

config.json

908 Bytes

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
generation_config.json

119 Bytes

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
merges.txt

456 kB

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
model.safetensors

498 MB
xet

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
special_tokens_map.json

131 Bytes

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
tokenizer.json

2.11 MB

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
tokenizer_config.json

476 Bytes

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "trl.trainer.sft_config.SFTConfig",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.43 kB
xet

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago
vocab.json

798 kB

Added SFT, Reward Model, and PPO-Aligned Model 3 months ago