Text Generation
Transformers
Safetensors
English
French
cn
llama
transformer
text-generation-inference
Instructions to use JiZha/SQLGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JiZha/SQLGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JiZha/SQLGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JiZha/SQLGPT") model = AutoModelForCausalLM.from_pretrained("JiZha/SQLGPT") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use JiZha/SQLGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JiZha/SQLGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JiZha/SQLGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/JiZha/SQLGPT
- SGLang
How to use JiZha/SQLGPT 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 "JiZha/SQLGPT" \ --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": "JiZha/SQLGPT", "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 "JiZha/SQLGPT" \ --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": "JiZha/SQLGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use JiZha/SQLGPT with Docker Model Runner:
docker model run hf.co/JiZha/SQLGPT
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("JiZha/SQLGPT")
model = AutoModelForCausalLM.from_pretrained("JiZha/SQLGPT")Quick Links
sqlgpt 介绍
SQLGPT 是一个用于 text2SQL 的模型。
模型底座
它是基于 deepseek 模型构建的,该模型通过使用qlora进行训练。
训练数据
训练数据包含了spider 数据集。这个模型的目标是将自然语言查询转换为SQL查询。
功能
Text to SQL( 以下简称Text2SQL),是将自然语言文本(Text)转换成结构化查询语言SQL的过程,属于自然语言处理-语义分析(Semantic Parsing)领域中的子任务。 它的目的可以简单概括为:“打破人与结构化数据之间的壁垒”,即普通用户可以通过自然语言描述完成复杂数据库的查询工作,得到想要的结果。 它通过学习语法、语义和查询意图来理解用户的问题,并根据对应的数据库结构生成相应的SQL查询语句。SQL-Codellama的训练过程经过了大量的数据预处理、特征提取和模型训练,以提高其准确性和性能。 它可以应用于各种领域,如数据分析、数据库查询优化等。SQL-Codellama的设计和训练过程是为了使其能够处理复杂的查询,并产生高质量的SQL查询结果。它的目标是为用户提供准确、高效的文本到SQL转换,从而帮助用户更轻松地进行数据库查询和数据分析。
git clone https://www.modelscope.cn/tomatoModelScope/sql_codellama.git
- Downloads last month
- 5
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JiZha/SQLGPT")