YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
🛠️ Model Details
- Base Model:
skt/A.X-4.0-Light - Model Size: 7.26B
- Fine-tuned by: kkh27
- Training Framework: Hugging Face Transformers + PEFT (LoRA)
- Precision: bfloat16 (bf16)
- Language: Korean
🧪 Training Configuration
🔧 LoRA Configuration
| Parameter | Value |
|---|---|
Rank (r) |
16 |
| Alpha | 32 |
| Dropout | 0.05 |
| Bias | none |
| Task Type | CAUSAL_LM |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
⚙️ Training Arguments
| Argument | Value |
|---|---|
| Per device train batch size | 8 |
| Gradient accumulation steps | 1 |
| Epochs | 3 |
| Learning rate | 5e-6 |
| Weight decay | 0.1 |
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support