Instructions to use nobodynosql/sql_codellama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nobodynosql/sql_codellama with Transformers:

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

pipe = pipeline("text-generation", model="nobodynosql/sql_codellama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nobodynosql/sql_codellama")
model = AutoModelForCausalLM.from_pretrained("nobodynosql/sql_codellama")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nobodynosql/sql_codellama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nobodynosql/sql_codellama

SGLang

How to use nobodynosql/sql_codellama 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 "nobodynosql/sql_codellama" \
    --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": "nobodynosql/sql_codellama",
		"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 "nobodynosql/sql_codellama" \
        --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": "nobodynosql/sql_codellama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nobodynosql/sql_codellama with Docker Model Runner:
```
docker model run hf.co/nobodynosql/sql_codellama
```

Jintao Huang commited on Oct 25, 2023

Commit

7cc83e4

1 Parent(s): 19ea727

fix readme yaml

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ containers:
 - registry-vpc.cn-shanghai.aliyuncs.com/cloud-dsw/tensorflow:1.12-cpu-py36-ubuntu18.04
 customized-quickstart: False
 finetune-support: False
-license: Apache License 2.0
 language:
 - en
 - fr
@@ -22,7 +22,6 @@ language:
 tags:
 - transformer
 pre-train: False
-datasets:
 train:
 - spider dataset
 - bird dataset
@@ -41,4 +40,4 @@ Text to SQL( 以下简称Text2SQL)，是将自然语言文本（Text）转换成
 ```bash
  git clone https://www.modelscope.cn/tomatoModelScope/sql_codellama.git
-```

 - registry-vpc.cn-shanghai.aliyuncs.com/cloud-dsw/tensorflow:1.12-cpu-py36-ubuntu18.04
 customized-quickstart: False
 finetune-support: False
+license: apache-2.0
 language:
 - en
 - fr
 tags:
 - transformer
 pre-train: False
 train:
 - spider dataset
 - bird dataset
 ```bash
  git clone https://www.modelscope.cn/tomatoModelScope/sql_codellama.git
+```