louisguthmann
/

qwen3.5-2b-shellcommand-linux-lora

Text Generation

Model card Files Files and versions

qwen3.5-2b-shellcommand-linux-lora

215 MB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

louisguthmann's picture

Update 2B adapter with repair_v3b full run

432b303 verified 4 days ago

checkpoint-120
Update 2B adapter with repair_v3b full run 4 days ago
eval
Update 2B adapter with repair_v3b full run 4 days ago
.gitattributes

1.64 kB
Update 2B adapter with repair_v3b full run 4 days ago
README.md

811 Bytes
Update 2B adapter with repair_v3b full run 4 days ago
adapter_config.json

1.05 kB
Update 2B adapter with repair_v3b full run 4 days ago
adapter_model.safetensors

43.7 MB
xet

Update 2B adapter with repair_v3b full run 4 days ago
chat_template.jinja

7.76 kB
Upload Qwen3.5-2B ShellCommand-Linux LoRA 4 days ago
tokenizer.json

20 MB
xet

Upload Qwen3.5-2B ShellCommand-Linux LoRA 4 days ago
tokenizer_config.json

1.1 kB
Upload Qwen3.5-2B ShellCommand-Linux LoRA 4 days ago
training_args.bin
Detected Pickle imports (10)
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "trl.trainer.sft_config.SFTConfig",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.71 kB
xet

Update 2B adapter with repair_v3b full run 4 days ago