nabeelshan
/

rlhf-gpt2-pipeline

Text Generation

reinforcement-learning

instruction-tuning

Model card Files Files and versions

rlhf-gpt2-pipeline / reward_model_final

3.25 MB

2 contributors

History: 4 commits

Nabeel Shan

Change RM Adapter extension

f35cb12 about 2 months ago

README.md

5.08 kB

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago
adapter_config.json

745 Bytes

Change Reward Model Base Path about 2 months ago
adapter_model.safetensors

1.78 MB
xet

Change RM Adapter extension about 2 months ago
merges.txt

456 kB

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago
special_tokens_map.json

470 Bytes

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago
tokenizer_config.json

525 Bytes

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.training_args.OptimizerNames",
- "trl.trainer.reward_config.RewardConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.24 kB
xet

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago
vocab.json

999 kB

Added SFT, Reward Model, and PPO-Aligned Model about 2 months ago