Instructions to use support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ")
model = AutoModelForCausalLM.from_pretrained("support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ

SGLang

How to use support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ 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 "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ" \
    --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": "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ",
		"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 "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ" \
        --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": "support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ with Docker Model Runner:
```
docker model run hf.co/support-pvelocity/Code-Llama-2-13B-instruct-text2sql-GPTQ
```

support-pvelocity commited on Nov 7, 2023

Commit

23f8d2d

1 Parent(s): 3383f0d

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -52,6 +52,10 @@ This model is governed by a custom commercial license from Code Llama. For detai
 ## Example Code
 You can use the Code-Llama-2-13B-instruct-text2sql-GPTQ model to generate SQL queries from natural language questions, as demonstrated in the following code snippet:
 ```python
 from transformers import AutoTokenizer
 from auto_gptq import AutoGPTQForCausalLM

 ## Example Code
 You can use the Code-Llama-2-13B-instruct-text2sql-GPTQ model to generate SQL queries from natural language questions, as demonstrated in the following code snippet:
+```cmd
+pip install -q transformers==4.35.0 torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 optimum==1.13.2 auto-gptq==0.4.2
+```
 ```python
 from transformers import AutoTokenizer
 from auto_gptq import AutoGPTQForCausalLM