Instructions to use WizardLMTeam/WizardMath-70B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WizardLMTeam/WizardMath-70B-V1.0 with Transformers:

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

pipe = pipeline("text-generation", model="WizardLMTeam/WizardMath-70B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WizardLMTeam/WizardMath-70B-V1.0")
model = AutoModelForCausalLM.from_pretrained("WizardLMTeam/WizardMath-70B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WizardLMTeam/WizardMath-70B-V1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WizardLMTeam/WizardMath-70B-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/WizardMath-70B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WizardLMTeam/WizardMath-70B-V1.0

SGLang

How to use WizardLMTeam/WizardMath-70B-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/WizardMath-70B-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/WizardMath-70B-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/WizardMath-70B-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/WizardMath-70B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WizardLMTeam/WizardMath-70B-V1.0 with Docker Model Runner:
```
docker model run hf.co/WizardLMTeam/WizardMath-70B-V1.0
```

Token Limit Lower Than Base Model?

#15

by JamesConley - opened Oct 4, 2023

Discussion

JamesConley

Oct 4, 2023

I noticed inside the config that "max_position_embeddings": 2048,". The base 70b model has a 4096 token length (see https://huggingface.co/meta-llama/Llama-2-70b-chat-hf/blob/main/config.json).
Was this intentionally reduced? Additionally, the tokenizer is indicating an even lower token limit (see below)
Token indices sequence length is longer than the specified maximum sequence length for this model (2661 > 1500). Running this sequence through the model will result in indexing errors

JamesConley changed discussion title from Token Limit to Token Limit Lower Than Base Model? Oct 4, 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