vicgalle
/

configurable-preference-qwen3-4b

Text Generation

Model card Files Files and versions Community

configurable-preference-qwen3-4b

Ctrl+K

Ctrl+K

2 contributors

History: 4 commits

vicgalle's picture

nielsr's picture

nielsr HF Staff

Add pipeline tag, library name, license, link to paper and Github repo (#1)

971f693 verified about 2 months ago

.gitattributes

1.57 kB

Upload 10 files 3 months ago
README.md

444 Bytes

Add pipeline tag, library name, license, link to paper and Github repo (#1) about 2 months ago
adapter_config.json

863 Bytes

Upload 10 files 3 months ago
adapter_model.safetensors

264 MB
LFS

Upload 10 files 3 months ago
added_tokens.json

707 Bytes

Upload 10 files 3 months ago
merges.txt

1.67 MB

Upload 10 files 3 months ago
special_tokens_map.json

614 Bytes

Upload 10 files 3 months ago
tokenizer.json

11.4 MB
LFS

Upload 10 files 3 months ago
tokenizer_config.json

10.3 kB

Upload 10 files 3 months ago
training_args.bin
Detected Pickle imports (11)
- "torch.device",
- "UnslothDPOTrainer.UnslothDPOConfig",
- "trl.trainer.dpo_config.FDivergenceType",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
6.67 kB
LFS

Upload 10 files 3 months ago
vocab.json

2.78 MB

Upload 10 files 3 months ago