Instructions to use rabbitcat/DataSmith-6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rabbitcat/DataSmith-6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rabbitcat/DataSmith-6b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rabbitcat/DataSmith-6b") model = AutoModelForCausalLM.from_pretrained("rabbitcat/DataSmith-6b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rabbitcat/DataSmith-6b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rabbitcat/DataSmith-6b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rabbitcat/DataSmith-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rabbitcat/DataSmith-6b
- SGLang
How to use rabbitcat/DataSmith-6b 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 "rabbitcat/DataSmith-6b" \ --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": "rabbitcat/DataSmith-6b", "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 "rabbitcat/DataSmith-6b" \ --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": "rabbitcat/DataSmith-6b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rabbitcat/DataSmith-6b with Docker Model Runner:
docker model run hf.co/rabbitcat/DataSmith-6b
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ DataSmith is a large model designed to generate JSON-format data from textual co
|
|
| 10 |
## Models Available
|
| 11 |
- DataSmith-6B
|
| 12 |
- Hugging Face Model Hub: [DataSmith-6B](https://huggingface.co/rabbitcat/DataSmith-6b)
|
|
|
|
| 13 |
|
| 14 |
## Usage
|
| 15 |
You can use the model directly or load it with device and dtype settings. The following is an example of generating questions and answers based on text content. You also can use `quick_start_demo.py` to generate question and answer pairs based on text content.
|
|
|
|
| 10 |
## Models Available
|
| 11 |
- DataSmith-6B
|
| 12 |
- Hugging Face Model Hub: [DataSmith-6B](https://huggingface.co/rabbitcat/DataSmith-6b)
|
| 13 |
+
- github:[DataSmith](https://github.com/element-factory/DataSmith)
|
| 14 |
|
| 15 |
## Usage
|
| 16 |
You can use the model directly or load it with device and dtype settings. The following is an example of generating questions and answers based on text content. You also can use `quick_start_demo.py` to generate question and answer pairs based on text content.
|