Zickl
/

llama32-1b-dpo-llm-judge

preference-learning

Model card Files Files and versions

llama32-1b-dpo-llm-judge

30.9 MB

1 contributor

History: 3 commits

Zickl's picture

Upload README.md with huggingface_hub

c5d17a7 verified 17 days ago

.gitattributes

1.57 kB

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
README.md

2.26 kB

Upload README.md with huggingface_hub 17 days ago
adapter_config.json

1.01 kB

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
adapter_model.safetensors

13.6 MB
xet

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
chat_template.jinja

3.83 kB

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
special_tokens_map.json

325 Bytes

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
tokenizer.json

17.2 MB
xet

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
tokenizer_config.json

50.6 kB

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago
training_args.bin
Detected Pickle imports (11)
- "transformers.trainer_utils.HubStrategy",
- "trl.trainer.dpo_config.DPOConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "trl.trainer.dpo_config.FDivergenceType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "accelerate.state.PartialState"
How to fix it?
6.8 kB
xet

Upload DPO fine-tuned model (LLM Judge dataset) 17 days ago