Instructions to use vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery with Transformers:

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

pipe = pipeline("text-generation", model="vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery")
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("vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery")
model = AutoModelForCausalLM.from_pretrained("vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery", 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 vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery

SGLang

How to use vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery 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 "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery" \
    --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": "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery",
		"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 "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery" \
        --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": "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery with Docker Model Runner:
```
docker model run hf.co/vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Uploaded model

Developed by: vishal042002
License: apache-2.0
Finetuned from model : unsloth/llama-3.2-3b-instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

The model was trained on a custom dataset containing clinical surgery Q&A pairs. The dataset was compiled from: Open-source medical books

RUNNING THE MODEL THROUGH ADAPTER MERGE:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model_name = "unsloth/Llama-3.2-3B-Instruct"  
base_model = AutoModelForCausalLM.from_pretrained(base_model_name, torch_dtype=torch.float16, device_map="auto")

adapter_path = "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery"
base_model = PeftModel.from_pretrained(base_model, adapter_path)

tokenizer = AutoTokenizer.from_pretrained(base_model_name)

device = "cuda" if torch.cuda.is_available() else "cpu"
base_model.to(device)

# Sample usage
input_text = "What is the mortality rate for patients requiring surgical intervention who were unstable preoperatively?"
inputs = tokenizer(input_text, return_tensors="pt").to(device)

outputs = base_model.generate(**inputs, max_new_tokens=200, temperature=1.5, top_p=0.9)
decoded_output = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(decoded_output)

LOADING THE MODEL DIRECTLY:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(model_name)

This model is designed to:

Answer questions about clinical surgery procedures. Provide information about surgical interventions.

Limitations:

The model should not be used as a substitute for professional medical advice. Responses should be verified by qualified medical professionals.

Downloads last month: 22

Safetensors

Model size

3B params

Tensor type

F16

Model tree for vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery

Quantizations

1 model

vishal042002
/

Llama3.2-3b-Instruct-ClinicalSurgery

Uploaded model

Model tree for vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery

Dataset used to train vishal042002/Llama3.2-3b-Instruct-ClinicalSurgery