Instructions to use AI-Sweden-Models/Llama-3-8B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI-Sweden-Models/Llama-3-8B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="AI-Sweden-Models/Llama-3-8B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AI-Sweden-Models/Llama-3-8B-instruct")
model = AutoModelForCausalLM.from_pretrained("AI-Sweden-Models/Llama-3-8B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AI-Sweden-Models/Llama-3-8B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AI-Sweden-Models/Llama-3-8B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AI-Sweden-Models/Llama-3-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AI-Sweden-Models/Llama-3-8B-instruct

SGLang

How to use AI-Sweden-Models/Llama-3-8B-instruct 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 "AI-Sweden-Models/Llama-3-8B-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AI-Sweden-Models/Llama-3-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "AI-Sweden-Models/Llama-3-8B-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AI-Sweden-Models/Llama-3-8B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AI-Sweden-Models/Llama-3-8B-instruct with Docker Model Runner:
```
docker model run hf.co/AI-Sweden-Models/Llama-3-8B-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Checkpoint 1

Training setup

The training was perfomed on the LUMI supercomputer within the DeployAI EU project. Based of the base model AI-Sweden-Models/Llama-3-8B.

How to use

import transformers
import torch

model_id = "AI-Sweden-Models/Llama-3-8B-instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Du är en hjälpsam assistant som svarar klokt och vänligt."},
    {"role": "user", "content": "Hur gör man pannkakor? Och vad behöver man handla? Undrar också vad 5+6 är.."},
]

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][-1])

>>> "För att göra pannkakor behöver du följande ingredienser:
- 1 kopp vetemjöl
- 1 tesked bakpulver
- 1/4 tesked salt
- 1 kopp mjölk
- 1 stort ägg
- 2 matskedar smält smör eller olja

För att börja, blanda vetemjölet, bakpulvret och saltet i en bunke. I en annan skål, vispa ihop mjölken, ägget och smöret eller oljan. 
Tillsätt de våta ingredienserna till de torra ingredienserna och blanda tills det är väl blandat. 
Låt smeten vila i cirka 10 minuter.

För att göra pannkakorna, värm en non-stick-panna eller stekpanna över medelvärme. 
När den är varm, häll smeten på pannan och grädda tills kanterna börjar torka ut och toppen är fast. 
Vänd pannkakan med en stekspade och grädda den andra sidan tills den är gyllenbrun. 
Upprepa med resten av smeten.

När det gäller 5+6 är svaret 11."