Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
NotoriousH2
/
gemma-3-1b-it-Math-GRPO
like
0
Safetensors
NotoriousH2/HRM8K
Korean
gemma3_text
math
korean
grpo
rl
gemma
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
gemma-3-1b-it-Math-GRPO
2.04 GB
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
NotoriousH2
Update README with detailed data pipeline and reproduction steps
bab0696
verified
9 days ago
.gitattributes
Safe
1.57 kB
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
README.md
Safe
2.47 kB
Update README with detailed data pipeline and reproduction steps
9 days ago
added_tokens.json
Safe
35 Bytes
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
chat_template.jinja
Safe
1.53 kB
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
config.json
Safe
1.6 kB
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
eval.py
Safe
3.47 kB
Add eval.py
9 days ago
generation_config.json
Safe
217 Bytes
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
model.safetensors
2 GB
xet
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
rs_sample.py
Safe
3.72 kB
Add rs_sample.py
9 days ago
special_tokens_map.json
Safe
548 Bytes
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
tokenizer.json
Safe
33.4 MB
xet
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
tokenizer.model
Safe
4.69 MB
xet
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
tokenizer_config.json
Safe
1.16 MB
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
train_grpo.py
Safe
5.6 kB
Add train_grpo.py
9 days ago
train_rs_sft.py
Safe
6.41 kB
Add train_rs_sft.py
9 days ago
train_sft.py
Safe
3.32 kB
Add train_sft.py
9 days ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
,
"trl.trainer.grpo_config.GRPOConfig"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"torch.device"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
7.63 kB
xet
SFT + RS-SFT + GRPO (500 steps, beta=0.04). GSM8K ~46.2%
9 days ago
