QomSSLab
/

Legal-gemma3-12b-it-lora-thinking

Model card Files Files and versions

Metrics Training metrics Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Fine-tuned Model: Legal-gemma3-12b-it-lora-thinking

📚 Training Configuration

data_path: QomSSLab/Legal_DS_SFT
output_dir: gemma312b_lora_chckpnts
new_model_name: Legal-gemma3-12b-it-lora-thinking
data_ratio: 1.0
model_name: QomSSLab/Legal-gemma3-12b-pt-v2
use_4bit: False
use_lora: True
max_seq_length: 8500
batch_size: 1
gradient_accu: 8
epochs: 2
learning_rate: 5e-05
lora_alpha: 64
lora_drop: 0.05
lora_r: 64
tune_embedding_layer: False
hf_token: ********
resume_from_checkpoint: False
use_8bit_optimizer: True
push_to_hub: True

Auto-generated after training.

Downloads last month: 330

Safetensors

Model size

12B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support