Instructions to use WizardLMTeam/WizardLM-13B-V1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardLM-13B-V1.2 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardLM-13B-V1.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardLM-13B-V1.2")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardLM-13B-V1.2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WizardLMTeam/WizardLM-13B-V1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WizardLMTeam/WizardLM-13B-V1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WizardLMTeam/WizardLM-13B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardLM-13B-V1.2

SGLang

How to use WizardLMTeam/WizardLM-13B-V1.2 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/WizardLM-13B-V1.2" \
    --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/WizardLM-13B-V1.2",
		"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/WizardLM-13B-V1.2" \
        --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/WizardLM-13B-V1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardLM-13B-V1.2 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardLM-13B-V1.2
```

mat1 and mat2 shapes cannot be multiplied (38x5120 and 1x2560)

#13

by LaferriereJC - opened Aug 12, 2023

Discussion

LaferriereJC

Aug 12, 2023

    RuntimeError: mat1 and mat2 shapes cannot be multiplied (38x5120 and 1x2560)
    Output generated in 0.36 seconds (0.00 tokens/s, 0 tokens, context 38, seed 1942857980)

LaferriereJC changed discussion title from error when attempting to run model quantized to error when attempting to run model quantized mat1 and mat2 shapes cannot be multiplied (38x5120 and 1x2560) Aug 12, 2023

LaferriereJC changed discussion title from error when attempting to run model quantized mat1 and mat2 shapes cannot be multiplied (38x5120 and 1x2560) to mat1 and mat2 shapes cannot be multiplied (38x5120 and 1x2560) Aug 12, 2023

His-Wardship

Aug 17, 2023

In the file config.json, change the value of "pretraining_tp" (currently on line 18) from 2 to 1. This should fix it.

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