Instructions to use NadavShaked/D_Nikud with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NadavShaked/D_Nikud with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NadavShaked/D_Nikud")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("NadavShaked/D_Nikud") model = AutoModel.from_pretrained("NadavShaked/D_Nikud") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NadavShaked/D_Nikud with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NadavShaked/D_Nikud" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NadavShaked/D_Nikud", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NadavShaked/D_Nikud
- SGLang
How to use NadavShaked/D_Nikud 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 "NadavShaked/D_Nikud" \ --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": "NadavShaked/D_Nikud", "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 "NadavShaked/D_Nikud" \ --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": "NadavShaked/D_Nikud", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NadavShaked/D_Nikud with Docker Model Runner:
docker model run hf.co/NadavShaked/D_Nikud
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ Our D-Nikud model utilizes the TevBERT architecture and Bi-LSTM for diacritizati
|
|
| 40 |
|
| 41 |
## Pre Trained model
|
| 42 |
|
| 43 |
-
Our pre-trained D-Nikud model can be found at [Link](https://drive.google.com/drive/folders/
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|
|
|
|
| 40 |
|
| 41 |
## Pre Trained model
|
| 42 |
|
| 43 |
+
Our pre-trained D-Nikud model can be found at [Link](https://drive.google.com/drive/folders/1IKR-Zz27I5K25OVDOs5mYs70VwrQRjlt?usp=sharing). To use it, unzip the downloaded file and copy the contents to the 'models' folder.
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|