Instructions to use llmware/slim-sql-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llmware/slim-sql-onnx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="llmware/slim-sql-onnx")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("llmware/slim-sql-onnx") model = AutoModelForCausalLM.from_pretrained("llmware/slim-sql-onnx") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use llmware/slim-sql-onnx with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llmware/slim-sql-onnx" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llmware/slim-sql-onnx", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/llmware/slim-sql-onnx
- SGLang
How to use llmware/slim-sql-onnx 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 "llmware/slim-sql-onnx" \ --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": "llmware/slim-sql-onnx", "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 "llmware/slim-sql-onnx" \ --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": "llmware/slim-sql-onnx", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use llmware/slim-sql-onnx with Docker Model Runner:
docker model run hf.co/llmware/slim-sql-onnx
Upload README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
inference: false
|
| 4 |
+
tags: [green, p1, llmware-fx, ov, emerald]
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# slim-sql-ov
|
| 8 |
+
|
| 9 |
+
**slim-sql-ov** is a small specialized function calling model that takes as input a table schema and a natural language query, and outputs a SQL statement that corresponds to the query, and can be run against a database table. This is a very small text-to-sql model designed for reasonable accuracy on single tables and relatively straightforward queries, and for easy integration into multi-step processes.
|
| 10 |
+
|
| 11 |
+
This is an OpenVino int4 quantized version of slim-sql-1b-v0, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
- **Developed by:** llmware
|
| 17 |
+
- **Model type:** tinyllama
|
| 18 |
+
- **Parameters:** 1.1 billion
|
| 19 |
+
- **Model Parent:** llmware/slim-sql-1b-v0
|
| 20 |
+
- **Language(s) (NLP):** English
|
| 21 |
+
- **License:** Apache 2.0
|
| 22 |
+
- **Uses:** Text-to-SQL conversion
|
| 23 |
+
- **RAG Benchmark Accuracy Score:** NA
|
| 24 |
+
- **Quantization:** int4
|
| 25 |
+
|
| 26 |
+
## Model Card Contact
|
| 27 |
+
|
| 28 |
+
[llmware on github](https://www.github.com/llmware-ai/llmware)
|
| 29 |
+
|
| 30 |
+
[llmware on hf](https://www.huggingface.co/llmware)
|
| 31 |
+
|
| 32 |
+
[llmware website](https://www.llmware.ai)
|