Instructions to use WizardLMTeam/WizardCoder-15B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardCoder-15B-V1.0 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardCoder-15B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardCoder-15B-V1.0")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardCoder-15B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WizardLMTeam/WizardCoder-15B-V1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WizardLMTeam/WizardCoder-15B-V1.0"
# 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-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardCoder-15B-V1.0

SGLang

How to use WizardLMTeam/WizardCoder-15B-V1.0 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-15B-V1.0" \
    --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-15B-V1.0",
		"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-15B-V1.0" \
        --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-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardCoder-15B-V1.0 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardCoder-15B-V1.0
```

Parallel Inferences using GPU?

#38

by vermanic - opened Sep 7, 2023

Discussion

vermanic

Sep 7, 2023

•

edited Sep 7, 2023

So, I have this basic question that if I call the infer() function parallely using multiple threads, Will that work?

Code:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

checkpoint = "WizardLM/WizardCoder-15B-V1.0"
device = "cuda" if torch.cuda.is_available() else "cpu"  # "cuda:X" for GPU usage or "cpu" for CPU usage


class Model:
    def __init__(self):
        print("Running in " + device)
        self.tokenizer = AutoTokenizer.from_pretrained(checkpoint)
        self.model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map='auto')

    def infer(self, input_text, token_count):
        inputs = self.tokenizer.encode(input_text, return_tensors="pt").to(device)
        outputs = self.model.generate(inputs, max_new_tokens=token_count)
        return self.tokenizer.decode(outputs[0])

Also, max_new_tokens means the number of tokens I want the model to respond with, right?

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