Instructions to use ruslanmv/llama3-8B-medical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ruslanmv/llama3-8B-medical with Transformers:

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

pipe = pipeline("text-generation", model="ruslanmv/llama3-8B-medical")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ruslanmv/llama3-8B-medical")
model = AutoModelForCausalLM.from_pretrained("ruslanmv/llama3-8B-medical")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ruslanmv/llama3-8B-medical with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ruslanmv/llama3-8B-medical"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ruslanmv/llama3-8B-medical",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ruslanmv/llama3-8B-medical

SGLang

How to use ruslanmv/llama3-8B-medical 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 "ruslanmv/llama3-8B-medical" \
    --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": "ruslanmv/llama3-8B-medical",
		"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 "ruslanmv/llama3-8B-medical" \
        --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": "ruslanmv/llama3-8B-medical",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ruslanmv/llama3-8B-medical with Docker Model Runner:
```
docker model run hf.co/ruslanmv/llama3-8B-medical
```

ruslanmv commited on May 15, 2024

Commit

e003c82

verified ·

1 Parent(s): ce9a9e6

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -10,8 +10,6 @@ tags:
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
 - ruslanmv/ai-medical-chatbot
-pipeline_tag: text-generation
 model-index:
 - name: llama3-8B-medical
   results: []

 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
 - ruslanmv/ai-medical-chatbot
 model-index:
 - name: llama3-8B-medical
   results: []