Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ItsMaxNorm
/
DeepSeek-R1-Distill-SmolLM3-3B-GRPO
like
0
Text Generation
Transformers
open-r1/OpenR1-Math-220k
smollm3
Generated from Trainer
open-r1
trl
sft
conversational
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
DeepSeek-R1-Distill-SmolLM3-3B-GRPO
36.9 GB
1 contributor
History:
4 commits
ItsMaxNorm
End of training
2a13241
verified
5 months ago
global_step460
Model save
5 months ago
.gitattributes
1.57 kB
Training in progress, epoch 1
5 months ago
README.md
1.67 kB
End of training
5 months ago
all_results.json
215 Bytes
Model save
5 months ago
chat_template.jinja
2.15 kB
Training in progress, epoch 1
5 months ago
config.json
1.88 kB
End of training
5 months ago
generation_config.json
177 Bytes
Model save
5 months ago
latest
14 Bytes
Model save
5 months ago
special_tokens_map.json
289 Bytes
Training in progress, epoch 1
5 months ago
tokenizer.json
17.2 MB
xet
Training in progress, epoch 1
5 months ago
tokenizer_config.json
50.4 kB
Training in progress, epoch 1
5 months ago
train_results.json
215 Bytes
Model save
5 months ago
trainer_state.json
94.7 kB
Model save
5 months ago
training_args.bin
9.91 kB
xet
Training in progress, epoch 1
5 months ago
zero_to_fp32.py
33.3 kB
Model save
5 months ago
