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, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B", device_map="auto")

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
```

wierd Answer from meta llama - 8b

#113

by Akashgola001 - opened May 4, 2024

Discussion

Akashgola001

May 4, 2024

Upon conducting a recent check, I came across the model of Meta Llama 8B. As part of my testing, I prompted the system with the question, "Hey, how are you doing today?" To my surprise, the response I received was quite unusual and unsettling. The answer seemed to be filled with a sense of fear and unease, which left me feeling quite perplexed and concerned. Despite this unexpected outcome.

JaaackXD

May 5, 2024

Use the instruct model instead; you need more prompts to make the model productive.

Or help the girl anyway.

angrybyte

May 9, 2024

Wow, looks like your GPU needs an exorcism.

kaamraan

May 15, 2024

Try to use the instruction version and I recommend you to generate the text by using "repetition_penalty". I usually put it equal to 1.2. This way you will not have repetition problem.

huggingfacemodeltester

May 30, 2024

•

edited May 30, 2024

I guess you haven't interacted much with the base models

this is a normal behavior of a base model, it just tries to randomly autocomplete your sentence. what you need is a chat model (also called instruct model often), which has the assistant personality

upd: oops, just realized i'm necroposting, never mind

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