Instructions to use Qwen/CodeQwen1.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/CodeQwen1.5-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/CodeQwen1.5-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Qwen/CodeQwen1.5-7B") model = AutoModelForCausalLM.from_pretrained("Qwen/CodeQwen1.5-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/CodeQwen1.5-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/CodeQwen1.5-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/CodeQwen1.5-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/CodeQwen1.5-7B
- SGLang
How to use Qwen/CodeQwen1.5-7B 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 "Qwen/CodeQwen1.5-7B" \ --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": "Qwen/CodeQwen1.5-7B", "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 "Qwen/CodeQwen1.5-7B" \ --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": "Qwen/CodeQwen1.5-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/CodeQwen1.5-7B with Docker Model Runner:
docker model run hf.co/Qwen/CodeQwen1.5-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ CodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based d
|
|
| 20 |
* Strong code generation capabilities and competitve performance across a series of benchmarks;
|
| 21 |
* Supporting long context understanding and generation with the context length of 64K tokens;
|
| 22 |
* Supporting 92 coding languages
|
| 23 |
-
* Excellent performance
|
| 24 |
|
| 25 |
|
| 26 |
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
|
|
|
|
| 20 |
* Strong code generation capabilities and competitve performance across a series of benchmarks;
|
| 21 |
* Supporting long context understanding and generation with the context length of 64K tokens;
|
| 22 |
* Supporting 92 coding languages
|
| 23 |
+
* Excellent performance in text-to-SQL, bug fix, etc.
|
| 24 |
|
| 25 |
|
| 26 |
For more details, please refer to our [blog post](https://qwenlm.github.io/blog/codeqwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
|