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
```

WC models are heavily biased towards old standards/code samples

by FizzyFolk - opened Jan 7, 2024

Discussion

FizzyFolk

Jan 7, 2024

Wizard coder despite claiming title of best model still miserably fails to use its knowledge of newer standards/versions/approaches when it comes to actual code, heavily biased towards pre 2022 scenarios, libraries, etc. Even GPT-4 fails in that department and even at level of JS spec.

dillfrescott

Jan 7, 2024

Most likely dataset age issues possibly.

imoc

Jan 16, 2024

well, 1995 till now🌚

deleted

Jan 16, 2024

may not help you, but in the case of python code i always tell models to use version 3.. so i dont get v2 code or a mixture.

And as others have said ( and not just here ), it wont be 'current' the dataset will cut off at a point in time. Its just the way of things..

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment