Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
kenhktsui
/
Qwen-0.5B-GRPO
like
1
Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2402.03300
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
Qwen-0.5B-GRPO
1 contributor
History:
2 commits
kenhktsui
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
a000783
verified
14 days ago
.gitattributes
1.57 kB
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
README.md
2.22 kB
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
added_tokens.json
605 Bytes
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
config.json
731 Bytes
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
generation_config.json
242 Bytes
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
merges.txt
1.67 MB
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
model.safetensors
988 MB
LFS
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
special_tokens_map.json
496 Bytes
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
tokenizer.json
11.4 MB
LFS
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
tokenizer_config.json
7.33 kB
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
training_args.bin
pickle
Detected Pickle imports (10)
"trl.trainer.grpo_config.GRPOConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SaveStrategy"
How to fix it?
5.56 kB
LFS
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago
vocab.json
2.78 MB
kenhktsui/Qwen-0.5B-GRPO-gsm8k-correct-reward
14 days ago