RohithMidigudla/gemma-health-telugu-medical-mix-h1-30-h2-70-lora
Weighted LoRA adapter mix for Gemma health Telugu medical work.
This is intentionally published as an adapter, not a full merged 16-bit model. The full merge path produced invalid generations during pure inference probes.
Mix
- Candidate:
h1_30_h2_70 - Telugu/H1 adapter:
RohithMidigudla/gemma-health-telugu-lora-h1 - Medical/H2 adapter:
RohithMidigudla/gemma-health-medical-lora-h2 - Telugu weight:
0.3 - Medical weight:
0.7
Validate with pure generation before using this adapter as a GRPO base.
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-E4B-it") model = PeftModel.from_pretrained(base_model, "RohithMidigudla/gemma-health-telugu-medical-mix-h1-30-h2-70-lora")