Instructions to use richardr1126/spider-skeleton-wizard-coder-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardr1126/spider-skeleton-wizard-coder-8bit with Transformers:

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

pipe = pipeline("text-generation", model="richardr1126/spider-skeleton-wizard-coder-8bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("richardr1126/spider-skeleton-wizard-coder-8bit")
model = AutoModelForCausalLM.from_pretrained("richardr1126/spider-skeleton-wizard-coder-8bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use richardr1126/spider-skeleton-wizard-coder-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "richardr1126/spider-skeleton-wizard-coder-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "richardr1126/spider-skeleton-wizard-coder-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/richardr1126/spider-skeleton-wizard-coder-8bit

SGLang

How to use richardr1126/spider-skeleton-wizard-coder-8bit 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 "richardr1126/spider-skeleton-wizard-coder-8bit" \
    --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": "richardr1126/spider-skeleton-wizard-coder-8bit",
		"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 "richardr1126/spider-skeleton-wizard-coder-8bit" \
        --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": "richardr1126/spider-skeleton-wizard-coder-8bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use richardr1126/spider-skeleton-wizard-coder-8bit with Docker Model Runner:
```
docker model run hf.co/richardr1126/spider-skeleton-wizard-coder-8bit
```

richardr1126 commited on Jul 26, 2023

Commit

aa42541

1 Parent(s): 9469cf6

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -28,6 +28,17 @@ The goal of the Spider challenge is to develop natural language interfaces to cr
 This dataset was used to finetune this model.
 ## Citations
 ```

 This dataset was used to finetune this model.
+### Spider Skeleton WizardCoder - [test-suite-sql-eval](https://github.com/taoyds/test-suite-sql-eval) Results
+With temperature set to 0.0, top_p set to 0.9, and top_k set to 0, the model achieves **61% execution accuracy** on the Spider dev set.
+<img src="https://raw.githubusercontent.com/cuplv/text-to-sql-wizardcoder/main/eval/plots/spiderwizard-plus-chatgpt.svg" height="300">
+<img src="https://raw.githubusercontent.com/cuplv/text-to-sql-wizardcoder/main/eval/plots/spiderwizard-vs-chatgpt.svg" height="300">
+Note:
+- ChatGPT was evaluated with the default hyperparameters and with the system message `You are a sophisticated AI assistant capable of converting text into SQL queries. You can only output SQL, don't add any other text.`
+- Both models were evaluated with `--plug_value` in `evaluation.py` using the Spider dev set with database context.
+  - `--plug_value`: If set, the gold value will be plugged into the predicted query. This is suitable if your model does not predict values. This is set to `False` by default.
 ## Citations
 ```