Instructions to use WizardLMTeam/WizardCoder-33B-V1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardCoder-33B-V1.1 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardCoder-33B-V1.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardCoder-33B-V1.1")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardCoder-33B-V1.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WizardLMTeam/WizardCoder-33B-V1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WizardLMTeam/WizardCoder-33B-V1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WizardLMTeam/WizardCoder-33B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardCoder-33B-V1.1

SGLang

How to use WizardLMTeam/WizardCoder-33B-V1.1 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 "WizardLMTeam/WizardCoder-33B-V1.1" \
    --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": "WizardLMTeam/WizardCoder-33B-V1.1",
		"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 "WizardLMTeam/WizardCoder-33B-V1.1" \
        --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": "WizardLMTeam/WizardCoder-33B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardCoder-33B-V1.1 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardCoder-33B-V1.1
```

Ziyang commited on Jan 4, 2024

Commit

2146494

1 Parent(s): c071560

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -77,6 +77,8 @@ Please use **the same systems prompts strictly** with us, and we do not guarante
 We provide all codes [here](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder/src).
 ```
 transformers==4.36.2
 vllm==0.2.5

 We provide all codes [here](https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder/src).
+We also provide all generated [results](https://github.com/nlpxucan/WizardLM/blob/main/WizardCoder/data/humaneval_mbpp_wizardcoder33b_v1.1_results.zip).
 ```
 transformers==4.36.2
 vllm==0.2.5