Instructions to use thebnbrkr/hippocratically_llama3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thebnbrkr/hippocratically_llama3.2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="thebnbrkr/hippocratically_llama3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("thebnbrkr/hippocratically_llama3.2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thebnbrkr/hippocratically_llama3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thebnbrkr/hippocratically_llama3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thebnbrkr/hippocratically_llama3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thebnbrkr/hippocratically_llama3.2

SGLang

How to use thebnbrkr/hippocratically_llama3.2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "thebnbrkr/hippocratically_llama3.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thebnbrkr/hippocratically_llama3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "thebnbrkr/hippocratically_llama3.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thebnbrkr/hippocratically_llama3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thebnbrkr/hippocratically_llama3.2 with Docker Model Runner:
```
docker model run hf.co/thebnbrkr/hippocratically_llama3.2
```

Hippocratically LLaMA 3.2: Medical Chatbot (LoRA Fine-tuned)

Model: thebnbrkr/hippocratically_llama3.2
Base: meta-llama/Llama-3.2-3B-Instruct
Fine-tuning: LoRA (via PEFT + TRL’s SFTTrainer)
Dataset: ruslanmv/ai-medical-chatbot (public medical Q&A)

Model Description

hippocratically_llama3.2 is a LoRA-finetuned version of Meta’s LLaMA 3.2B-Instruct model, adapted for clinical dialogue and general medical question-answering. It uses instruction-tuning and parameter-efficient fine-tuning (PEFT) methods to create a compact and responsive healthcare assistant for research and educational use.

Intended Use

Medical Q&A chatbot simulations
Research on LoRA-based instruction tuning
Prompt evaluation in clinical contexts
LLM alignment/hallucination analysis

Limitations

Not suitable for clinical deployment
May hallucinate outdated or unsafe information
Doesn't prioritize emergencies unless prompted
Lacks real-time patient data or diagnostic context

Training Details

Base model: meta-llama/Llama-3.2-3B-Instruct
Fine-tuning method: LoRA (r=8, alpha=16, dropout 0.05)
Target modules: q_proj, v_proj
Trainer: SFTTrainer from trl
Batch size: 2
Epochs: 1
Learning rate: 2e-4
Precision: fp16
Output dir: ./llama3.2-medical-chat

Example Prompt:

prompt: | How can someone determine their metabolic rate?

Example response:

Metabolic rate can be determined in several ways, depending on the context and level of precision required.

Basal Metabolic Rate (BMR): This is the number of calories your body needs at rest. A commonly used formula to estimate BMR for women is:

BMR = 655 + (4.35 × weight in lbs) + (4.7 × height in inches) – (4.7 × age in years)

For men:

BMR = 66 + (6.23 × weight in lbs) + (12.7 × height in inches) – (6.8 × age in years)
Harris-Benedict Equation: This builds on BMR to estimate Total Daily Energy Expenditure (TDEE) by multiplying the BMR by an activity factor (e.g., 1.2 for sedentary, 1.55 for moderate activity).
Clinical Methods: More accurate tests, like indirect calorimetry, measure oxygen consumption and carbon dioxide production to calculate actual energy expenditure.
Wearables and Apps: Fitness trackers and smart devices offer real-time estimates, though they are less precise.

Always consult a healthcare provider for personalized metabolic assessments or weight management planning.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for thebnbrkr/hippocratically_llama3.2

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1910)

this model

thebnbrkr
/

hippocratically_llama3.2