Instructions to use microsoft/wavecoder-ultra-6.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/wavecoder-ultra-6.7b with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/wavecoder-ultra-6.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/wavecoder-ultra-6.7b")
model = AutoModelForCausalLM.from_pretrained("microsoft/wavecoder-ultra-6.7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/wavecoder-ultra-6.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/wavecoder-ultra-6.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/wavecoder-ultra-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/wavecoder-ultra-6.7b

SGLang

How to use microsoft/wavecoder-ultra-6.7b 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 "microsoft/wavecoder-ultra-6.7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/wavecoder-ultra-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "microsoft/wavecoder-ultra-6.7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/wavecoder-ultra-6.7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/wavecoder-ultra-6.7b with Docker Model Runner:
```
docker model run hf.co/microsoft/wavecoder-ultra-6.7b
```

Difference between Ultra and Pro models?

by barsmonster - opened Apr 20, 2024

Discussion

barsmonster

Apr 20, 2024

Could you please clarify?

zjy2001

Apr 21, 2024

Please refer to https://twitter.com/TeamCodeLLM_AI/status/1747551286877450647.

ethanc8

May 17, 2024

•

edited May 17, 2024

For those who can't view Twitter, here's the content of the tweets:

🌊🌊🌊Introduce WaveCoder-Ultra-6.7B with the closest capabilities to GPT-4 so far.
Arxiv:arxiv.org/abs/2312.14187
WaveCoder-Ultra-6.7B is the newest SOTA open-source Code LLM on mutiple tasks.
WaveCoder-DS-6.7B=DeepseekCoder-6.7B+CodeOcean
WaveCoder-Pro-6.7B=DeepseekCoder-6.7B+GPT-4 enhanced CodeOcean
WaveCoder-Ultra-6.7B=DeepseekCoder-6.7B+GPT-4 enhanced CodeOcean+Code Evol-instruct
We are in the process of preparing for open-source related matters. Please stay tuned. Once everything is ready, we will announce the latest updates through this account.

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