Instructions to use juierror/flan-t5-text2sql-with-schema-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juierror/flan-t5-text2sql-with-schema-v2 with Transformers:

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

pipe = pipeline("text-generation", model="juierror/flan-t5-text2sql-with-schema-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("juierror/flan-t5-text2sql-with-schema-v2")
model = AutoModelForSeq2SeqLM.from_pretrained("juierror/flan-t5-text2sql-with-schema-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use juierror/flan-t5-text2sql-with-schema-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juierror/flan-t5-text2sql-with-schema-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juierror/flan-t5-text2sql-with-schema-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/juierror/flan-t5-text2sql-with-schema-v2

SGLang

How to use juierror/flan-t5-text2sql-with-schema-v2 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 "juierror/flan-t5-text2sql-with-schema-v2" \
    --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": "juierror/flan-t5-text2sql-with-schema-v2",
		"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 "juierror/flan-t5-text2sql-with-schema-v2" \
        --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": "juierror/flan-t5-text2sql-with-schema-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use juierror/flan-t5-text2sql-with-schema-v2 with Docker Model Runner:
```
docker model run hf.co/juierror/flan-t5-text2sql-with-schema-v2
```

Fine-tuning theory

by KhimNguyen - opened Apr 4, 2024

Discussion

KhimNguyen

Apr 4, 2024

Hi, I am new to NLP. I would like to know more about theory aspect of your work. When you fine-tune the model, how to identify which layers are trained and which layers of LLM are frozen? Thank you so much in advance.

juierror

Owner Apr 4, 2024

@KhimNguyen

Hi, to be frank, I didn't look into each layer much, but from my understanding, the pretrained model already have some knowledge, so I fine-tune all the layers with the input format that I want with small learning rate.

However, as you pointed out, we might achieve better results if we freeze some layers of the encoder model. I think it is depends on experiment and select the best way to tune a model.

KhimNguyen

Apr 13, 2024

Hi, sorry for disturbing you again. I replicate your code in github to train my own model but I have a question about evaluating model cause I don't see you use any metrics to evaluate the efficiency of your model. Which metric should I use if I want to assess my model? Thank you so much in advance.

juierror

Owner Apr 13, 2024

@KhimNguyen

since this is a text generative task, I think you can use bleu score to evaluate model

you can check this for more information
https://huggingface.co/spaces/evaluate-metric/bleu

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment