tahamajs
/

Qwen3-4b-gsm8k-Qlora-GRPO

Text Generation

Model card Files Files and versions

Qwen3-4b-gsm8k-Qlora-GRPO

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

tahamajs's picture

Update Readme

eea9430 verified 20 days ago

.gitattributes

1.57 kB

Continue training: +5k steps on extra math data 21 days ago
README.md

11.2 kB

Update Readme 20 days ago
adapter_config.json

943 Bytes

add files 20 days ago
adapter_model.safetensors

66.1 MB
xet

add files 20 days ago
added_tokens.json

707 Bytes

Continue training: +5k steps on extra math data 21 days ago
chat_template.jinja

4.67 kB

Continue training: +5k steps on extra math data 21 days ago
merges.txt

1.67 MB

Continue training: +5k steps on extra math data 21 days ago
special_tokens_map.json

614 Bytes

Continue training: +5k steps on extra math data 21 days ago
tokenizer.json

11.4 MB
xet

add files 20 days ago
tokenizer_config.json

5.43 kB

Continue training: +5k steps on extra math data 21 days ago
trainer_state.json

18.9 kB

add files 20 days ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames",
- "UnslothGRPOTrainer.UnslothGRPOConfig",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
7.06 kB
xet

add files 20 days ago
vocab.json

2.78 MB

Continue training: +5k steps on extra math data 21 days ago