Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
atrost
/
math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-True
like
0
Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
trl
conversational
text-generation-inference
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-True
3.46 GB
1 contributor
History:
2 commits
atrost
Model save
fa4613d
verified
about 2 months ago
.gitattributes
Safe
1.57 kB
Model save
about 2 months ago
README.md
Safe
1.82 kB
Model save
about 2 months ago
added_tokens.json
Safe
707 Bytes
Model save
about 2 months ago
chat_template.jinja
Safe
4.12 kB
Model save
about 2 months ago
config.json
Safe
1.36 kB
Model save
about 2 months ago
generation_config.json
Safe
127 Bytes
Model save
about 2 months ago
merges.txt
Safe
1.67 MB
Model save
about 2 months ago
model.safetensors
3.44 GB
xet
Model save
about 2 months ago
special_tokens_map.json
Safe
616 Bytes
Model save
about 2 months ago
tokenizer.json
Safe
11.4 MB
xet
Model save
about 2 months ago
tokenizer_config.json
Safe
5.41 kB
Model save
about 2 months ago
training_args.bin
6.42 kB
xet
Model save
about 2 months ago
vocab.json
Safe
2.78 MB
Model save
about 2 months ago
