CryptoYogi
/

vazhi-v5_0-lora

Text Generation

Model card Files Files and versions

vazhi-v5_0-lora

51.9 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

CryptoYogi's picture

SFT v5.0 adapter: vanilla Qwen3-0.6B, r=16, targets=7 modules, lr=1e-05, 1 epoch, 5328 samples

e0aec90 verified 2 months ago

.gitattributes

1.57 kB
Training in progress, step 666 2 months ago
README.md

5.2 kB
SFT v5.0 adapter: vanilla Qwen3-0.6B, r=16, targets=7 modules, lr=1e-05, 1 epoch, 5328 samples 2 months ago
adapter_config.json

1.05 kB
Training in progress, step 666 2 months ago
adapter_model.safetensors

40.4 MB
xet

Training in progress, step 666 2 months ago
chat_template.jinja

4.17 kB
Training in progress, step 666 2 months ago
tokenizer.json

11.4 MB
xet

Training in progress, step 666 2 months ago
tokenizer_config.json

665 Bytes
Training in progress, step 666 2 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "trl.trainer.sft_config.SFTConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
5.65 kB
xet

Training in progress, step 666 2 months ago
training_metadata.json

475 Bytes
SFT v5.0 adapter: vanilla Qwen3-0.6B, r=16, targets=7 modules, lr=1e-05, 1 epoch, 5328 samples 2 months ago