Text Generation
Transformers
Safetensors
English
Arabic
llama
llama-3-8b
sft
medical
text-generation-inference
Instructions to use Reverb/MedLLaMA-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Reverb/MedLLaMA-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Reverb/MedLLaMA-3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Reverb/MedLLaMA-3") model = AutoModelForCausalLM.from_pretrained("Reverb/MedLLaMA-3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Reverb/MedLLaMA-3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Reverb/MedLLaMA-3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Reverb/MedLLaMA-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Reverb/MedLLaMA-3
- SGLang
How to use Reverb/MedLLaMA-3 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 "Reverb/MedLLaMA-3" \ --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": "Reverb/MedLLaMA-3", "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 "Reverb/MedLLaMA-3" \ --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": "Reverb/MedLLaMA-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Reverb/MedLLaMA-3 with Docker Model Runner:
docker model run hf.co/Reverb/MedLLaMA-3
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,6 @@ datasets:
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# MedLLaMA-3
|
| 19 |
-
[<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com)
|
| 20 |
|
| 21 |
|
| 22 |
This model is developed by Basel Anaya.
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# MedLLaMA-3
|
|
|
|
| 19 |
|
| 20 |
|
| 21 |
This model is developed by Basel Anaya.
|