Instructions to use kaashh02/phi3-mini-medical-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaashh02/phi3-mini-medical-merged with Transformers:

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

pipe = pipeline("text-generation", model="kaashh02/phi3-mini-medical-merged", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaashh02/phi3-mini-medical-merged", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("kaashh02/phi3-mini-medical-merged", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kaashh02/phi3-mini-medical-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaashh02/phi3-mini-medical-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kaashh02/phi3-mini-medical-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kaashh02/phi3-mini-medical-merged

SGLang

How to use kaashh02/phi3-mini-medical-merged 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 "kaashh02/phi3-mini-medical-merged" \
    --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": "kaashh02/phi3-mini-medical-merged",
		"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 "kaashh02/phi3-mini-medical-merged" \
        --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": "kaashh02/phi3-mini-medical-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kaashh02/phi3-mini-medical-merged with Docker Model Runner:
```
docker model run hf.co/kaashh02/phi3-mini-medical-merged
```

phi3-mini-medical-merged

This is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct specialized for medical applications.

Model Details

Base Model: microsoft/Phi-3-mini-4k-instruct
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Specialization: Medical/Healthcare domain
Precision: 8-bit quantization during training

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "kaashh02/phi3-mini-medical-merged"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

# Example usage
prompt = "What are the symptoms of diabetes?"
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

Fine-tuned using LoRA adapters
Optimized for medical question-answering and healthcare information
Trained with 8-bit quantization for efficiency

Limitations

This model is intended for educational and research purposes
Should not be used as a substitute for professional medical advice
Always consult healthcare professionals for medical decisions

Citation

If you use this model, please cite:

@misc{phi3_mini_medical_merged,
  title={phi3-mini-medical-merged: Medical Fine-tuned Phi-3 Model},
  author={Your Name},
  year={2025},
  howpublished={\url{https://huggingface.co/kaashh02/phi3-mini-medical-merged}}
}

Downloads last month: 21

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for kaashh02/phi3-mini-medical-merged

Base model

microsoft/Phi-3-mini-4k-instruct

Adapter

(871)

this model