Instructions to use unsloth/llama-3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/llama-3-8b with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/llama-3-8b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3-8b")
model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/llama-3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/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": "unsloth/llama-3-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/llama-3-8b

SGLang

How to use unsloth/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 "unsloth/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": "unsloth/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 "unsloth/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": "unsloth/llama-3-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use unsloth/llama-3-8b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/llama-3-8b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/llama-3-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/llama-3-8b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/llama-3-8b",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/llama-3-8b with Docker Model Runner:
```
docker model run hf.co/unsloth/llama-3-8b
```

is this the llama-3-8b model clone?

by malhajar - opened Apr 18, 2024

Discussion

malhajar

Apr 18, 2024

lucasjin

Apr 19, 2024

No, this is false llama3

shimmyshimmer

Unsloth AI org Apr 19, 2024

:D

Yes, it is the clone but it is specifically designed for Unsloth users to train it 2xfaster with 60% less memory etc

shimmyshimmer

Unsloth AI org Apr 19, 2024

No, this is false llama3

Sorry what is this supposed to mean? :)

danielhanchen

Unsloth AI org Apr 19, 2024

Yes it's a clone :) But no gated access, and works seamlessly for Unsloth users

lucasjin

Apr 19, 2024

Am just throw a false alarm in case author didn't response.

jiluan

Apr 19, 2024

Performance seems worse than llama2-7b

lucasjin

Apr 21, 2024

This is base model

shimmyshimmer

Unsloth AI org Apr 21, 2024

This is base model

correct it is the base model!

shimmyshimmer

Unsloth AI org Apr 21, 2024

Performance seems worse than llama2-7b

Really? Do you happen to see in which areas?

ewre324

Apr 21, 2024

The performance of 8B Instruct models (unsloth) are much better than their llama2 counterpath, however logical reasoning is still not so good, for example asking which is heavier 1 kg feather or 2 kg feather yields wrong output.

upupbug

May 23, 2024

•

edited May 23, 2024

The hash code of the files between https://hf-mirror.com/unsloth/llama-3-8b/ and https://huggingface.co/meta-llama/Meta-Llama-3-8B/ is different,
so if you sure that it's a clone?
@shimmyshimmer

danielhanchen

Unsloth AI org May 23, 2024

•

edited May 23, 2024

@upupbug Oh sorry actually there is a difference - our base model trained the <eot> and <start_header> tokens since it was untrained in llama-3 base. We only editted the lm_head and embed_tokens for these 2 tokens

danielhanchen

Unsloth AI org Jun 7, 2024

@upupbug I reuploaded it and removed our changes! Instead I might manually edit the tokens in a future release

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