Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
NotoriousH2
/
gemma-3-1b-it-Math-RS-SFT
like
0
PyTorch
NotoriousH2/HRM8K
Korean
gemma3_text
math
korean
rejection-sampling
sft
gemma
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
gemma-3-1b-it-Math-RS-SFT
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
NotoriousH2
Update README with detailed data pipeline and reproduction steps
2d3e79d
verified
2 months ago
.gitattributes
Safe
1.57 kB
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
README.md
Safe
2.76 kB
Update README with detailed data pipeline and reproduction steps
2 months ago
added_tokens.json
Safe
35 Bytes
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
chat_template.jinja
Safe
1.53 kB
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
config.json
Safe
1.6 kB
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
eval.py
Safe
3.47 kB
Add eval.py
2 months ago
generation_config.json
Safe
217 Bytes
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
What is a pickle import?
2 GB
xet
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
rs_sample.py
Safe
3.72 kB
Add rs_sample.py
2 months ago
special_tokens_map.json
Safe
548 Bytes
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
tokenizer.json
Safe
33.4 MB
xet
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
tokenizer.model
Safe
4.69 MB
xet
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
tokenizer_config.json
Safe
1.16 MB
SFT + Rejection Sampling SFT (5x teacher replay). GSM8K avg ~46.6%, best 48.9%
2 months ago
train_rs_sft.py
Safe
6.41 kB
Add train_rs_sft.py
2 months ago
train_sft.py
Safe
3.32 kB
Add train_sft.py
2 months ago