Instructions to use Vezora/WaveCoder-6.7b-Ultra-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vezora/WaveCoder-6.7b-Ultra-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="Vezora/WaveCoder-6.7b-Ultra-bf16")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vezora/WaveCoder-6.7b-Ultra-bf16")
model = AutoModelForCausalLM.from_pretrained("Vezora/WaveCoder-6.7b-Ultra-bf16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vezora/WaveCoder-6.7b-Ultra-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vezora/WaveCoder-6.7b-Ultra-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vezora/WaveCoder-6.7b-Ultra-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vezora/WaveCoder-6.7b-Ultra-bf16

SGLang

How to use Vezora/WaveCoder-6.7b-Ultra-bf16 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 "Vezora/WaveCoder-6.7b-Ultra-bf16" \
    --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": "Vezora/WaveCoder-6.7b-Ultra-bf16",
		"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 "Vezora/WaveCoder-6.7b-Ultra-bf16" \
        --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": "Vezora/WaveCoder-6.7b-Ultra-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vezora/WaveCoder-6.7b-Ultra-bf16 with Docker Model Runner:
```
docker model run hf.co/Vezora/WaveCoder-6.7b-Ultra-bf16
```

Vezora commited on May 7, 2024

Commit

5664b4e

verified ·

1 Parent(s): ca09c2c

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 license: mit
-license_link: https://huggingface.co/microsoft/wavecoder-ultra-6.7b/blob/main/LICENSE
 language:
   - en
 library_name: transformers
@@ -13,6 +13,10 @@ metrics:
   - code_eval
 ---
 <h1 align="center">
 🌊 WaveCoder: Widespread And Versatile Enhanced Code LLM
 </h1>

 ---
 license: mit
+license_link: https://huggingface.co/Vezora/WaveCoder-6.7b-Ultra-bf16/blob/main/LICENSE
 language:
   - en
 library_name: transformers
   - code_eval
 ---
+## This is a Re-Upload of Wave-Coder-Ultra in bf16 since original model was uploaded in fp32 and there are none others available. Licensing remains the same as original base model.
 <h1 align="center">
 🌊 WaveCoder: Widespread And Versatile Enhanced Code LLM
 </h1>