Instructions to use meta-llama/Llama-3.1-405B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meta-llama/Llama-3.1-405B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-405B-FP8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-405B-FP8")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-405B-FP8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use meta-llama/Llama-3.1-405B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meta-llama/Llama-3.1-405B-FP8"
# 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/Llama-3.1-405B-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/meta-llama/Llama-3.1-405B-FP8

SGLang

How to use meta-llama/Llama-3.1-405B-FP8 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/Llama-3.1-405B-FP8" \
    --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/Llama-3.1-405B-FP8",
		"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/Llama-3.1-405B-FP8" \
        --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/Llama-3.1-405B-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use meta-llama/Llama-3.1-405B-FP8 with Docker Model Runner:
```
docker model run hf.co/meta-llama/Llama-3.1-405B-FP8
```

fix: set `clean_up_tokenization_spaces` to `false`

#21

by maxsloef - opened Mar 21

base: refs/heads/main

←

from: refs/pr/21

Discussion Files changed

-1

maxsloef

Mar 21

clean_up_tokenization_spaces=true causes tokenizer.decode() to silently strip spaces before punctuation, producing incorrect decoded text for Llama 3's BPE tokenizer. This was inherited from a HuggingFace transformers library default — Llama 2 had it set to false, and Llama 4 already ships with false.

See the full writeup with reproduction, impact analysis, and history: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct/discussions/356

The fix is a one-line change in tokenizer_config.json.

fix: set `clean_up_tokenization_spaces` to `false`a94efc65

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment