UVLabs/HyperLLM-4b at main

544 MB

1 contributor

History: 6 commits

bebis1's picture

Update README with corrected eval results (extraction bug fix)

b45908b verified about 15 hours ago

.gitattributes

1.57 kB

Initial release v0.1 - experimental 4 days ago
LICENSE

11 kB

Initial release v0.1 - experimental 4 days ago
README.md

8.02 kB

Update README with corrected eval results (extraction bug fix) about 15 hours ago
adapter_config.json

1.06 kB

Upload HyperLLM v0.3 - SFT+DPO trained model about 20 hours ago
adapter_model.safetensors

529 MB
xet

Upload HyperLLM v0.3 - SFT+DPO trained model about 20 hours ago
added_tokens.json

707 Bytes

Upload HyperLLM v0.2 about 22 hours ago
chat_template.jinja

2.63 kB

Upload HyperLLM v0.2 about 22 hours ago
merges.txt

1.67 MB

Upload HyperLLM v0.2 about 22 hours ago
special_tokens_map.json

613 Bytes

Upload HyperLLM v0.2 about 22 hours ago
tokenizer.json

11.4 MB
xet

Upload HyperLLM v0.3 - SFT+DPO trained model about 20 hours ago
tokenizer_config.json

666 Bytes

Upload HyperLLM v0.3 - SFT+DPO trained model about 20 hours ago
training_args.bin
Detected Pickle imports (10)
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "trl.trainer.dpo_config.DPOConfig"
How to fix it?
5.43 kB
xet

Upload HyperLLM v0.3 - SFT+DPO trained model about 20 hours ago
vocab.json

2.78 MB

Upload HyperLLM v0.2 about 22 hours ago