Text Generation
Transformers
PyTorch
sql
code
gpt_bigcode
SQL generation
Text-to-SQL
text2sql
text-generation-inference
Instructions to use seeklhy/codes-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seeklhy/codes-3b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="seeklhy/codes-3b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("seeklhy/codes-3b") model = AutoModelForCausalLM.from_pretrained("seeklhy/codes-3b") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use seeklhy/codes-3b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "seeklhy/codes-3b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "seeklhy/codes-3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/seeklhy/codes-3b
- SGLang
How to use seeklhy/codes-3b 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 "seeklhy/codes-3b" \ --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": "seeklhy/codes-3b", "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 "seeklhy/codes-3b" \ --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": "seeklhy/codes-3b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use seeklhy/codes-3b with Docker Model Runner:
docker model run hf.co/seeklhy/codes-3b
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- sql
|
| 4 |
+
- code
|
| 5 |
+
tags:
|
| 6 |
+
- SQL generation
|
| 7 |
+
- Text-to-SQL
|
| 8 |
+
- text2sql
|
| 9 |
+
license: "apache-2.0"
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# CodeS-3B
|
| 13 |
+
|
| 14 |
+
CodeS is a series of Code LLMs specifically optimized for SQL generation.
|
| 15 |
+
|
| 16 |
+
The CodeS encompasses 1B, 3B, 7B, and 15B scales. CodeS-1B, 3B, and 7B are incrementally pre-trained on the top of StarCoderBase-1B, 3B, and 7B and support the max length of 8,192. Meanwhile, CodeS-15B, derived from StarCoder-15B, accommodates sequences of up to 6,144 tokens.
|
| 17 |
+
|
| 18 |
+
We have demonstrated that CodeS achieves new state-of-the-art performance on two challenging Text-to-SQL benchmarks: Spider and Bird.
|
| 19 |
+
|
| 20 |
+
For more details about how to use CodeS, please refer to our GitHub page: https://github.com/RUCKBReasoning/codes.
|
| 21 |
+
|
| 22 |
+
(This is the repository of CodeS-3B.)
|
| 23 |
+
|