Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dipta007
/
dagger-4B_SFT_GRPO
like
0
Text Generation
Transformers
Safetensors
dipta007/dagger
dipta007/DistractMath-Bn
Bengali
English
gemma3
image-to-text
math
reasoning
computational-graph
bangla
low-resource
distractor-aware
small-model
conversational
text-generation-inference
arxiv:
2601.06853
License:
gemma
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
dagger-4B_SFT_GRPO
8.64 GB
2 contributors
History:
4 commits
dipta007
zabir-nabil
updated readme (
#1
)
39bf741
verified
1 day ago
.gitattributes
1.57 kB
Upload folder using huggingface_hub
12 days ago
README.md
7.36 kB
updated readme (#1)
1 day ago
added_tokens.json
35 Bytes
Upload folder using huggingface_hub
12 days ago
chat_template.jinja
1.53 kB
Upload folder using huggingface_hub
12 days ago
config.json
2.7 kB
Upload folder using huggingface_hub
12 days ago
model-00001-of-00002.safetensors
4.96 GB
xet
Upload folder using huggingface_hub
12 days ago
model-00002-of-00002.safetensors
3.64 GB
xet
Upload folder using huggingface_hub
12 days ago
model.safetensors.index.json
90.6 kB
Upload folder using huggingface_hub
12 days ago
preprocessor_config.json
570 Bytes
Upload folder using huggingface_hub
12 days ago
processor_config.json
70 Bytes
Upload folder using huggingface_hub
12 days ago
special_tokens_map.json
670 Bytes
Upload folder using huggingface_hub
12 days ago
tokenizer.json
33.4 MB
xet
Upload folder using huggingface_hub
12 days ago
tokenizer.model
4.69 MB
xet
Upload folder using huggingface_hub
12 days ago
tokenizer_config.json
1.16 MB
Upload folder using huggingface_hub
12 days ago