Instructions to use codefuse-ai/CodeFuse-QWen-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codefuse-ai/CodeFuse-QWen-14B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-QWen-14B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-QWen-14B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use codefuse-ai/CodeFuse-QWen-14B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "codefuse-ai/CodeFuse-QWen-14B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "codefuse-ai/CodeFuse-QWen-14B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/codefuse-ai/CodeFuse-QWen-14B
- SGLang
How to use codefuse-ai/CodeFuse-QWen-14B 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 "codefuse-ai/CodeFuse-QWen-14B" \ --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": "codefuse-ai/CodeFuse-QWen-14B", "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 "codefuse-ai/CodeFuse-QWen-14B" \ --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": "codefuse-ai/CodeFuse-QWen-14B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use codefuse-ai/CodeFuse-QWen-14B with Docker Model Runner:
docker model run hf.co/codefuse-ai/CodeFuse-QWen-14B
Commit Β·
a7aace4
1
Parent(s): 3b4b391
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ CodeFuse-QWen-14B is a 14B Code-LLM finetuned by QLoRA of multiple code tasks on
|
|
| 24 |
|
| 25 |
π₯π₯ 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
|
| 26 |
|
| 27 |
-
π₯π₯π₯ 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) of [CodeFuse-CodeLlama-34B](https://
|
| 28 |
|
| 29 |
π₯π₯π₯ 2023-09-11 [CodeFuse-CodeLlama34B](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B) has achived 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
|
| 30 |
|
|
|
|
| 24 |
|
| 25 |
π₯π₯ 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
|
| 26 |
|
| 27 |
+
π₯π₯π₯ 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) of [CodeFuse-CodeLlama-34B](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B). Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
|
| 28 |
|
| 29 |
π₯π₯π₯ 2023-09-11 [CodeFuse-CodeLlama34B](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B) has achived 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
|
| 30 |
|