Instructions to use meta-llama/Meta-Llama-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Meta-Llama-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3-8B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
model = AutoModelForMultimodalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meta-llama/Meta-Llama-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Meta-Llama-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meta-llama/Meta-Llama-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Meta-Llama-3-8B

SGLang

How to use meta-llama/Meta-Llama-3-8B 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 "meta-llama/Meta-Llama-3-8B" \
    --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": "meta-llama/Meta-Llama-3-8B",
		"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 "meta-llama/Meta-Llama-3-8B" \
        --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": "meta-llama/Meta-Llama-3-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/Meta-Llama-3-8B with Docker Model Runner:
```
docker model run hf.co/meta-llama/Meta-Llama-3-8B
```

Tokenizer.pad_token_id is NoneType, which requires float

#36

by tian9 - opened Apr 19, 2024

Discussion

tian9

Apr 19, 2024

•

edited Apr 19, 2024

Hello, I want to change the LLaVA base model from llama2 to llama3, but I encountered error during executing these lines:

input_ids = torch.nn.utils.rnn.pad_sequence(
input_ids,
batch_first=True,
padding_value=self.tokenizer.pad_token_id)

the llama3 tokenizer's pad_token_id is None, which can not be a valid input in this method. How can I resolve this problem?
The model and tokenizer is correctly loaded.

johngiorgi

Apr 20, 2024

The usual trick, which also applies here, is to use the EOS token, e.g. you can apply:

tokenizer.pad_token = tokenizer.pad_token or tokenizer.eos_token

Then tokenizer.pad_token_id will be set as eos_token_id automatically.

tian9

Apr 20, 2024

thanks a lot! your ans is very helpful

The usual trick, which also applies here, is to use the EOS token, e.g. you can apply:
tokenizer.pad_token = tokenizer.pad_token or tokenizer.eos_token
Then tokenizer.pad_token_id will be set as eos_token_id automatically.

tian9 changed discussion status to closed Apr 20, 2024

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