Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
neopolita
/
qwen2.5-3b-instruct-numinamath-tir-50p-lr16-la32-qkvo-gspo-x4
like
0
Transformers
Safetensors
Generated from Trainer
grpo
trl
arxiv:
2402.03300
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
qwen2.5-3b-instruct-numinamath-tir-50p-lr16-la32-qkvo-gspo-x4
Ctrl+K
Ctrl+K
1 contributor
History:
30 commits
neopolita
Training in progress, step 282
4d0a36e
verified
27 days ago
.gitattributes
Safe
1.57 kB
Training in progress, step 10
27 days ago
README.md
2.14 kB
Training in progress, step 10
27 days ago
adapter_config.json
857 Bytes
Training in progress, step 10
27 days ago
adapter_model.safetensors
29.5 MB
LFS
Training in progress, step 282
27 days ago
added_tokens.json
Safe
605 Bytes
Training in progress, step 10
27 days ago
chat_template.jinja
Safe
2.51 kB
Training in progress, step 10
27 days ago
merges.txt
Safe
1.67 MB
Training in progress, step 10
27 days ago
special_tokens_map.json
Safe
613 Bytes
Training in progress, step 10
27 days ago
tokenizer.json
Safe
11.4 MB
LFS
Training in progress, step 10
27 days ago
tokenizer_config.json
Safe
4.69 kB
Training in progress, step 10
27 days ago
training_args.bin
pickle
Detected Pickle imports (10)
"torch.device"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"trl.trainer.grpo_config.GRPOConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
How to fix it?
7.06 kB
LFS
Training in progress, step 10
27 days ago
vocab.json
Safe
2.78 MB
Training in progress, step 10
27 days ago