Shekswess
/

trlm-135m

Text Generation

preference-alignment

Generated from Trainer

text-generation-inference

Model card Files Files and versions

274 MB

1 contributor

History: 4 commits

Shekswess's picture

Training in progress, step 10

44da050 verified 23 days ago

runs
Training in progress, step 10 23 days ago
.gitattributes

1.52 kB

initial commit 24 days ago
README.md

1.91 kB

Training in progress, step 10 23 days ago
added_tokens.json

44 Bytes

Upload 12 files 24 days ago
chat_template.jinja

658 Bytes

Upload 12 files 24 days ago
config.json

873 Bytes

Training in progress, step 10 23 days ago
generation_config.json

142 Bytes

Upload 12 files 24 days ago
merges.txt

466 kB

Upload 12 files 24 days ago
model.safetensors

269 MB
xet

Training in progress, step 10 23 days ago
special_tokens_map.json

648 Bytes

Upload 12 files 24 days ago
tokenizer.json

3.52 MB

Training in progress, step 10 23 days ago
tokenizer_config.json

3.74 kB

Upload 12 files 24 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SaveStrategy",
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
7.19 kB
xet

Training in progress, step 10 23 days ago
vocab.json

801 kB

Upload 12 files 24 days ago