Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
dipta007
/
GanitLLM-0.6B_SFT_CGRPO
like
0
Text Generation
Transformers
Safetensors
dipta007/Ganit
Bengali
English
qwen3
math
bengali
reasoning
grpo
curriculum-learning
conversational
text-generation-inference
arxiv:
2601.06767
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
9246d61
GanitLLM-0.6B_SFT_CGRPO
1.52 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
dipta007
(Trained with Unsloth)
9246d61
verified
4 months ago
.gitattributes
Safe
1.57 kB
(Trained with Unsloth)
4 months ago
README.md
587 Bytes
Unsloth Model Card
4 months ago
added_tokens.json
Safe
707 Bytes
(Trained with Unsloth)
4 months ago
chat_template.jinja
Safe
4.17 kB
(Trained with Unsloth)
4 months ago
config.json
Safe
1.4 kB
(Trained with Unsloth)
4 months ago
merges.txt
Safe
1.67 MB
(Trained with Unsloth)
4 months ago
model.safetensors
1.5 GB
xet
(Trained with Unsloth)
4 months ago
special_tokens_map.json
Safe
613 Bytes
(Trained with Unsloth)
4 months ago
tokenizer.json
Safe
11.4 MB
xet
(Trained with Unsloth)
4 months ago
tokenizer_config.json
Safe
9.86 kB
(Trained with Unsloth)
4 months ago
vocab.json
Safe
2.78 MB
(Trained with Unsloth)
4 months ago
