hypertension

Hypertension LoRA Adapter

• Developed by: vyshnaviprasad
• License: apache-2.0
• Finetuned from model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit

This LLaMA model was trained 2x faster with Unsloth and Hugging Face's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

---

⚠️ Important

This is a LoRA adapter, not a full standalone model.

• On Hugging Face Inference API, the pipeline_tag and base_model allow it to work directly.
• Locally, you must load it with the base model for text generation.

---

How to Use Locally

from unsloth import FastLanguageModel

base_model = "unsloth/meta-llama-3.1-8b-instruct-bnb-4bit"
adapter_model = "vyshnaviprasad/hypertension"

# Load base model with LoRA adapter
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=base_model,
    adapter_name=adapter_model,
    load_in_4bit=True
)

FastLanguageModel.for_inference(model)

# Generate text
prompt = "Explain hypertension in simple words to a patient."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=1000)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))