Instructions to use eglym/DR-TEXT2SQL-CodeLlama2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eglym/DR-TEXT2SQL-CodeLlama2-7B with Transformers:

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

pipe = pipeline("text-generation", model="eglym/DR-TEXT2SQL-CodeLlama2-7B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eglym/DR-TEXT2SQL-CodeLlama2-7B")
model = AutoModelForCausalLM.from_pretrained("eglym/DR-TEXT2SQL-CodeLlama2-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eglym/DR-TEXT2SQL-CodeLlama2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eglym/DR-TEXT2SQL-CodeLlama2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eglym/DR-TEXT2SQL-CodeLlama2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eglym/DR-TEXT2SQL-CodeLlama2-7B

SGLang

How to use eglym/DR-TEXT2SQL-CodeLlama2-7B 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 "eglym/DR-TEXT2SQL-CodeLlama2-7B" \
    --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": "eglym/DR-TEXT2SQL-CodeLlama2-7B",
		"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 "eglym/DR-TEXT2SQL-CodeLlama2-7B" \
        --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": "eglym/DR-TEXT2SQL-CodeLlama2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eglym/DR-TEXT2SQL-CodeLlama2-7B with Docker Model Runner:
```
docker model run hf.co/eglym/DR-TEXT2SQL-CodeLlama2-7B
```

DR-TEXT2SQL-CodeLlama2-7B / README.md

eglym

Update README.md

f2c6cc4 verified about 2 years ago

preview code

Raw History Blame Contribute Delete

2.01 kB

---
license: cc-by-sa-4.0
datasets:
- xlangai/spider
language:
- en
base_model:
- codellama/CodeLlama-7b-Instruct-hf
pipeline_tag: text-generation
library_name: transformers
tags:
- code
---
# Update notice
The model weights were updated at 3 AM UTC on Sep 12, 2024. 

# Model Card for DR-TEXT2SQL-CodeLlama2-7B
A capable large language model for natural language to SQL generation.


## Model Details
### Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: eglym
Model type: [Text to SQL]
License: [CC-by-SA-4.0]
Finetuned from model: [CodeLlama-7B]

Uses
This model is intended to be used by non-technical users to understand data inside their SQL databases. It is meant as an analytics tool, and not as a database admin tool.

This model has not been trained to reject malicious requests from users with write access to databases, and should only be used by users with read-only access.

How to Get Started with the Model
Use the code here to get started with the model.

Prompt
Please use the following prompt for optimal results. Please remember to use do_sample=False and num_beams=4 for optimal results.

### Task
Generate a SQL query to answer user_question.
### Answer
Given the database schema, here is the SQL query that realize user_question.

Evaluation
This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.

You can read more about the methodology behind SQLEval here.

Results
We classified each generated question into one of 6 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
```bash
        easy    medium    hard    extra    all
count   250     440       174     170      1034
compare etype exec
===================== EXECUTION ACCURACY =====================
exec    0.899   0.805     0.655   0.464    0.748
```

	---
	license: cc-by-sa-4.0
	datasets:
	- xlangai/spider
	language:
	- en
	base_model:
	- codellama/CodeLlama-7b-Instruct-hf
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- code
	---

	# Update notice
	The model weights were updated at 3 AM UTC on Sep 12, 2024.

	# Model Card for DR-TEXT2SQL-CodeLlama2-7B
	A capable large language model for natural language to SQL generation.


	## Model Details
	### Model Description
	This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

	Developed by: eglym
	Model type: [Text to SQL]
	License: [CC-by-SA-4.0]
	Finetuned from model: [CodeLlama-7B]

	Uses
	This model is intended to be used by non-technical users to understand data inside their SQL databases. It is meant as an analytics tool, and not as a database admin tool.

	This model has not been trained to reject malicious requests from users with write access to databases, and should only be used by users with read-only access.

	How to Get Started with the Model
	Use the code here to get started with the model.

	Prompt
	Please use the following prompt for optimal results. Please remember to use do_sample=False and num_beams=4 for optimal results.

	### Task
	Generate a SQL query to answer user_question.


	### Answer
	Given the database schema, here is the SQL query that realize user_question.

	Evaluation
	This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.

	You can read more about the methodology behind SQLEval here.

	Results
	We classified each generated question into one of 6 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
	```bash

	easy medium hard extra all
	count 250 440 174 170 1034
	compare etype exec
	===================== EXECUTION ACCURACY =====================
	exec 0.899 0.805 0.655 0.464 0.748
	```