Instructions to use Mreeb/Medi-llama-2-7b-custom100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mreeb/Medi-llama-2-7b-custom100 with Transformers:

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

pipe = pipeline("text-generation", model="Mreeb/Medi-llama-2-7b-custom100")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mreeb/Medi-llama-2-7b-custom100")
model = AutoModelForCausalLM.from_pretrained("Mreeb/Medi-llama-2-7b-custom100")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mreeb/Medi-llama-2-7b-custom100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mreeb/Medi-llama-2-7b-custom100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mreeb/Medi-llama-2-7b-custom100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mreeb/Medi-llama-2-7b-custom100

SGLang

How to use Mreeb/Medi-llama-2-7b-custom100 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 "Mreeb/Medi-llama-2-7b-custom100" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mreeb/Medi-llama-2-7b-custom100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Mreeb/Medi-llama-2-7b-custom100" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mreeb/Medi-llama-2-7b-custom100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mreeb/Medi-llama-2-7b-custom100 with Docker Model Runner:
```
docker model run hf.co/Mreeb/Medi-llama-2-7b-custom100
```

Model Card for Model ID

This model is a customized version of Llama2, fine-tuned specifically for dermatological applications. It is designed to understand, generate, and provide expert insights on various skin conditions, causes, symptoms, diagnoses, treatment options, and preventive measures.

Model Details

Model Description

Customized Dermatology Model (Fine-Tuned Llama2):

This specialized variant of the Llama2 model has been fine-tuned on a custom dataset specifically curated for dermatology and skin-related medical tasks. It is designed to excel in understanding, generating, and providing accurate information about a wide range of skin conditions, including their causes, symptoms, diagnoses, recommended treatments, and prevention methods.

Key Features and Focus:

Skin Health Expertise: The fine-tuned model is tailored to be an expert in dermatology and skin health. It can provide insights, diagnoses, and recommendations related to various skin disorders and conditions.

Medical Knowledge: It incorporates medical knowledge relevant to dermatology, making it capable of responding to queries about the causes, symptoms, and best practices for managing and treating skin conditions.

Customized Responses: The model generates custom responses specific to dermatological inquiries, ensuring that the information it provides is accurate, up-to-date, and reliable.

Patient Education: It can assist in educating patients about skin health, suitable skincare routines, lifestyle choices, and dietary recommendations for maintaining or improving their skin condition.

Fine-Tuning Benefits: The model's fine-tuning process enhances its performance, making it a valuable tool for healthcare professionals, researchers, and individuals seeking information and guidance on skin-related medical topics.

This customized model is well-suited for a range of applications within the field of dermatology, including virtual dermatology consultations, patient education, and assisting healthcare providers in making informed decisions regarding skin health. It is designed to be a valuable resource for accurate and reliable information about skin conditions and related medical matters.

Downloads last month: 3