Instructions to use nikitaredy/medictron-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikitaredy/medictron-7B with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("BioMistral/BioMistral-7B")
model = PeftModel.from_pretrained(base_model, "nikitaredy/medictron-7B")

Transformers

How to use nikitaredy/medictron-7B with Transformers:

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

pipe = pipeline("text-generation", model="nikitaredy/medictron-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nikitaredy/medictron-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nikitaredy/medictron-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nikitaredy/medictron-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikitaredy/medictron-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nikitaredy/medictron-7B

SGLang

How to use nikitaredy/medictron-7B 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 "nikitaredy/medictron-7B" \
    --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": "nikitaredy/medictron-7B",
		"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 "nikitaredy/medictron-7B" \
        --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": "nikitaredy/medictron-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use nikitaredy/medictron-7B with Docker Model Runner:
```
docker model run hf.co/nikitaredy/medictron-7B
```

nikitaredy commited on Jun 20

Commit

5cc562d

verified ·

1 Parent(s): e6ecb52

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -23,8 +23,9 @@ language:
 A domain-adapted clinical LLM fine-tuned on synthetic Indian medical Q&A records using QLoRA (4-bit quantization) with Unsloth 2x speedup. Built to power the conversational AI layer of VitalKiosk — a contactless medical screening kiosk for senior and rural patients in India.
-> 📄 Used in research: **"VitalKiosk: An AI-Powered Contactless Medical Screening Kiosk with rPPG-Based Vital Sign Estimation and Conversational Clinical Guidance"**
 ---
 ## Model Details

 A domain-adapted clinical LLM fine-tuned on synthetic Indian medical Q&A records using QLoRA (4-bit quantization) with Unsloth 2x speedup. Built to power the conversational AI layer of VitalKiosk — a contactless medical screening kiosk for senior and rural patients in India.
+## Research Paper
+📄 [VitalKiosk: An AI-Powered Contactless Medical Screening Kiosk with rPPG-Based Vital Sign Estimation and Conversational Clinical Guidance](https://drive.google.com/file/d/10dM-Bfl9i6Z4-cjwVtUJOuzh-CpV_Xa7/view?usp=sharing)
 ---
 ## Model Details