Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
AIM-Intelligence
/
COMPASS_gemma-3-4b-it_LoRA
like
2
Follow
AIM Intelligence
22
Image-Text-to-Text
Transformers
Safetensors
PEFT
AIM-Intelligence/COMPASS-Policy-aware-SFT
English
gemma3
Generated from Trainer
trl
unsloth
sft
lora
alignment
safety
policy-compliance
policy-alignment
compass
conversational
text-generation-inference
arxiv:
2601.01836
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
COMPASS_gemma-3-4b-it_LoRA
8.64 GB
Ctrl+K
Ctrl+K
2 contributors
History:
4 commits
Dasool
Update README.md
68d597d
verified
2 months ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
3 months ago
README.md
Safe
2.18 kB
Update README.md
2 months ago
added_tokens.json
Safe
35 Bytes
Upload folder using huggingface_hub
3 months ago
chat_template.jinja
Safe
1.53 kB
Upload folder using huggingface_hub
3 months ago
config.json
Safe
2.62 kB
Upload folder using huggingface_hub
3 months ago
model-00001-of-00002.safetensors
Safe
4.96 GB
xet
Upload folder using huggingface_hub
3 months ago
model-00002-of-00002.safetensors
Safe
3.64 GB
xet
Upload folder using huggingface_hub
3 months ago
model.safetensors.index.json
Safe
90.6 kB
Upload folder using huggingface_hub
3 months ago
preprocessor_config.json
Safe
570 Bytes
Upload folder using huggingface_hub
3 months ago
processor_config.json
Safe
70 Bytes
Upload folder using huggingface_hub
3 months ago
special_tokens_map.json
Safe
670 Bytes
Upload folder using huggingface_hub
3 months ago
tokenizer.json
Safe
33.4 MB
xet
Upload folder using huggingface_hub
3 months ago
tokenizer.model
Safe
4.69 MB
xet
Upload folder using huggingface_hub
3 months ago
tokenizer_config.json
Safe
1.16 MB
Upload folder using huggingface_hub
3 months ago
