Instructions to use bineric/NorskGPT-Llama3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bineric/NorskGPT-Llama3-8b with Transformers:

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

pipe = pipeline("text-generation", model="bineric/NorskGPT-Llama3-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bineric/NorskGPT-Llama3-8b")
model = AutoModelForCausalLM.from_pretrained("bineric/NorskGPT-Llama3-8b", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bineric/NorskGPT-Llama3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bineric/NorskGPT-Llama3-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bineric/NorskGPT-Llama3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bineric/NorskGPT-Llama3-8b

SGLang

How to use bineric/NorskGPT-Llama3-8b 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 "bineric/NorskGPT-Llama3-8b" \
    --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": "bineric/NorskGPT-Llama3-8b",
		"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 "bineric/NorskGPT-Llama3-8b" \
        --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": "bineric/NorskGPT-Llama3-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bineric/NorskGPT-Llama3-8b with Docker Model Runner:
```
docker model run hf.co/bineric/NorskGPT-Llama3-8b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NorskGPT-Llama-3-8b-v0.1

This model is a Norwegian variant of Meta-Llama-3-8B, fine-tuned on a carefully selected mix of Norwegian instruction pairs. The model is tuned to understand and generate text in Norwegain.

Intended Use

This model is free to use for personal and research use. However a commercial license is required for commerical applications. This model can be used as an assistant-like chat. Try it out :)

Prompt Template

<|im_start|>system
Du er NorskGPT ....<|im_end|>
<|im_start|>user
Hei<|im_end|>
<|im_start|>assistant
Hei, hva kan jeg hjelpe deg med?<|im_end|>

Sample script

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model_name = "bineric/NorskGPT-Llama3-8b"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "Du er NorskGPT - en AI bot som hjelper brukeren med å svare på spørsmål?"},
    {"role": "assistant", "content": "Hei, jeg er NorskGPT, hva kan jeg hjelpe deg med?"},
    {"role": "user", "content": "Fortell meg om Oslo"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Limitations

This is an LLM, not a knowledge model. It can not be expected to have more information about Norway than the base model.
It will generally preform better on tasks that involves summarization, question answering and chat, than on tasks that requires more knowledge about Norway, specific domains, or tasks where the model can answer freely.
The model is released as is, and would in most cases need prompt tuning to achieve optimal results.

License

Attribution-NonCommercial-ShareAlike 4.0 International

This model is free to use for personal and research use. However a commercial license is required for commerical applications.

You are free to:

Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material
The licensor cannot revoke these freedoms as long as you follow the license terms.

Under the following terms:

Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
NonCommercial — You may not use the material for commercial purposes .
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.