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
```

BOS is actually the EOS token by default

#30

by dblakely - opened Jan 10, 2024

Discussion

dblakely

Jan 10, 2024

Hi, when I load the tokenizer for this model, it appears the BOS and EOS tokens are the same (both are set to the EOS token).

Example:

>>> from transformers import AutoTokenizer
>>> model_name = "WizardLM/WizardLM-13B-V1.2"
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
>>> tokenizer.bos_token
'</s>'      # <-- this is the EOS token, not the BOS token
>>> tokenizer.bos_token_id
2
>>> tokenizer.eos_token
'</s>'
>>> tokenizer.eos_token_id
2

You can see this as well when you tokenize something:

>>> tokenizer.decode(tokenizer("This is an input").input_ids)
'</s> This is an input'

Looking at the special_tokens_map.json file, you can see:

{
  "bos_token": "</s>",
  "eos_token": "</s>",
  "pad_token": "<unk>",
  "unk_token": "</s>"
}

Is this the typo? The bos_token should be set to "<s>" instead should it not?

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