Ctrl+K

1 contributor

History: 2 commits

CarlOwOs

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0

8cfd4c9 verified 8 days ago

checkpoint-54
Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
checkpoint-7
Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
runs
Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
.gitattributes

1.7 kB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
README.md

1.71 kB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
adapter_config.json

852 Bytes

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
adapter_model.safetensors

40.4 MB
LFS

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
added_tokens.json

707 Bytes

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
chat_template.jinja

4.12 kB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
distillation_config.json

4.6 kB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
merges.txt

1.67 MB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
special_tokens_map.json

616 Bytes

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
tokenizer.json

11.4 MB
LFS

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
tokenizer_config.json

5.41 kB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.state.PartialState",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
5.3 kB
LFS

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago
vocab.json

2.78 MB

Upload distilled Qwen model (QLoRA) - α=0.7, T=4.0 8 days ago

Detected Pickle imports (10)