Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use SpassMedAI/MLMedLlama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SpassMedAI/MLMedLlama3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SpassMedAI/MLMedLlama3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SpassMedAI/MLMedLlama3") model = AutoModelForCausalLM.from_pretrained("SpassMedAI/MLMedLlama3") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SpassMedAI/MLMedLlama3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SpassMedAI/MLMedLlama3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SpassMedAI/MLMedLlama3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SpassMedAI/MLMedLlama3
- SGLang
How to use SpassMedAI/MLMedLlama3 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 "SpassMedAI/MLMedLlama3" \ --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": "SpassMedAI/MLMedLlama3", "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 "SpassMedAI/MLMedLlama3" \ --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": "SpassMedAI/MLMedLlama3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SpassMedAI/MLMedLlama3 with Docker Model Runner:
docker model run hf.co/SpassMedAI/MLMedLlama3
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ language:
|
|
| 11 |
|
| 12 |
# Model Card for Model ID
|
| 13 |
|
| 14 |
-
[MMedBench](https://huggingface.co/datasets/Henrychur/MMedBench) and [KoreanMedMCQA](https://huggingface.co/datasets/SpassMedAI/KorMedMCQA_Rationale) Instruction Fine-Tuned Llama3 8B 4Bit quantized model using QLoRA.
|
| 15 |
|
| 16 |
|
| 17 |
## Model Details
|
|
|
|
| 11 |
|
| 12 |
# Model Card for Model ID
|
| 13 |
|
| 14 |
+
[MMedBench](https://huggingface.co/datasets/Henrychur/MMedBench) and [KoreanMedMCQA](https://huggingface.co/datasets/SpassMedAI/KorMedMCQA_Rationale) Instruction Fine-Tuned Multilingual Llama3 8B 4Bit quantized model using QLoRA.
|
| 15 |
|
| 16 |
|
| 17 |
## Model Details
|