YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Model Details
- Base Model:
trillionslabs/Tri-7B - Model Size: 7.53B
- Fine-tuned by: zzhenxi
- 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, v_proj |
Training Arguments
| Argument | Value |
|---|---|
| Per device train batch size | 8 |
| Gradient accumulation steps | 2 |
| Epochs | 2 |
| Learning rate | 2e-4 |
| Weight decay | 0.1 |
Updates
- Previous version (v4) is in HealthcareLLM-v4-Tri-7B
- Enhanced output format consistency and improved generalized responses across diverse prompts.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support