Instructions to use WizardLMTeam/WizardCoder-Python-34B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardCoder-Python-34B-V1.0 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardCoder-Python-34B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardCoder-Python-34B-V1.0")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardCoder-Python-34B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WizardLMTeam/WizardCoder-Python-34B-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-Python-34B-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-Python-34B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardCoder-Python-34B-V1.0

SGLang

How to use WizardLMTeam/WizardCoder-Python-34B-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-Python-34B-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-Python-34B-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-Python-34B-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-Python-34B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardCoder-Python-34B-V1.0 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardCoder-Python-34B-V1.0
```

Context length is still 4096

by Shahrukh181 - opened Aug 27, 2023

Discussion

Shahrukh181

Aug 27, 2023

I am using TheBloke's quantization of this model and found that this model has a context length of 4096 without any changes to the code. I read that this model had 16k context length without any changes and could go up to 100k. why is that?

lucasjin

Aug 27, 2023

Is that WizardCoder34B quantized model?

Shahrukh181

Aug 28, 2023

yeah

mirek190

Aug 28, 2023

The bloke version gguf shows 16k context

WizardLM changed discussion status to closed Sep 14, 2023

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