Instructions to use gabrielpondc/NL2SQL-StarCoder-15B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gabrielpondc/NL2SQL-StarCoder-15B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="gabrielpondc/NL2SQL-StarCoder-15B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gabrielpondc/NL2SQL-StarCoder-15B")
model = AutoModelForCausalLM.from_pretrained("gabrielpondc/NL2SQL-StarCoder-15B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gabrielpondc/NL2SQL-StarCoder-15B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gabrielpondc/NL2SQL-StarCoder-15B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gabrielpondc/NL2SQL-StarCoder-15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gabrielpondc/NL2SQL-StarCoder-15B

SGLang

How to use gabrielpondc/NL2SQL-StarCoder-15B 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 "gabrielpondc/NL2SQL-StarCoder-15B" \
    --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": "gabrielpondc/NL2SQL-StarCoder-15B",
		"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 "gabrielpondc/NL2SQL-StarCoder-15B" \
        --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": "gabrielpondc/NL2SQL-StarCoder-15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gabrielpondc/NL2SQL-StarCoder-15B with Docker Model Runner:
```
docker model run hf.co/gabrielpondc/NL2SQL-StarCoder-15B
```

gabrielpondc commited on Apr 16, 2024

Commit

1991883

verified ·

1 Parent(s): 6644ecd

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -12,9 +12,9 @@ tasks:
 # Model Card for NL2SQL-StarCoder-15B
-## 模型介绍
-NL2SQL-StarCoder-15B 是在基础模型 StarCoder 上通过 QLoRA 对自然语言生成SQL任务进行微调的 15B Code-LLM。
 ## Requirements
@@ -22,9 +22,9 @@ NL2SQL-StarCoder-15B 是在基础模型 StarCoder 上通过 QLoRA 对自然语
 - pytorch>=2.0.0
 - transformers==4.32.0
 - CUDA 11.4
-## 推理数据格式
-推理数据为模型在训练数据格式下拼接的字符串形式，它也是推理时输入prompt拼接的方式：
 ```python
 """
 <|user|>
@@ -35,15 +35,15 @@ CREATE TABLE "table_name" (
 ...
 )
-/* Write a sql to answer the following question: {问题} */
 <|assistant|>
 ```sql
-{输出SQL}
 ```<|end|>
 """
 ```
-## 快速开始
 ```python
 import torch

 # Model Card for NL2SQL-StarCoder-15B
+## Model Inro
+NL2SQL-StarCoder-15B is a NLP-SQL model fintuned by QLoRAbased on StarCoder 15B Code-LLM。
 ## Requirements
 - pytorch>=2.0.0
 - transformers==4.32.0
 - CUDA 11.4
+## Data Format
+The data is in the form of a string spliced by the model in the training data format, which is also how the input PROMPT is spliced during inference:
 ```python
 """
 <|user|>
 ...
 )
+/* Write a sql to answer the following question: {Question} */
 <|assistant|>
 ```sql
+{Output SQL}
 ```<|end|>
 """
 ```
+## Quick Start
 ```python
 import torch