Instructions to use NbAiLab/nb-notram-llama-3.1-8b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NbAiLab/nb-notram-llama-3.1-8b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="NbAiLab/nb-notram-llama-3.1-8b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NbAiLab/nb-notram-llama-3.1-8b-instruct")
model = AutoModelForCausalLM.from_pretrained("NbAiLab/nb-notram-llama-3.1-8b-instruct", 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 NbAiLab/nb-notram-llama-3.1-8b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NbAiLab/nb-notram-llama-3.1-8b-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": "NbAiLab/nb-notram-llama-3.1-8b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NbAiLab/nb-notram-llama-3.1-8b-instruct

SGLang

How to use NbAiLab/nb-notram-llama-3.1-8b-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 "NbAiLab/nb-notram-llama-3.1-8b-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": "NbAiLab/nb-notram-llama-3.1-8b-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 "NbAiLab/nb-notram-llama-3.1-8b-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": "NbAiLab/nb-notram-llama-3.1-8b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NbAiLab/nb-notram-llama-3.1-8b-instruct with Docker Model Runner:
```
docker model run hf.co/NbAiLab/nb-notram-llama-3.1-8b-instruct
```

pere commited on Jan 9

Commit

809b460

verified ·

1 Parent(s): 3b82dd2

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -6,6 +6,7 @@ language:
   - "en"  # English
 tags:
   - "llama"
   - "norwegian"
   - "bokmål"
   - "nynorsk"
@@ -18,16 +19,16 @@ base_model: "meta-llama/Llama-3.1-8B-Instruct"
 library_name: "transformers"
 ---
-## Model Card: "NB-Llama-3.1-8B-Instruct"
 ### Model overview
-"NB-Llama-3.1-8B-Instruct" is part of the "NB-Llama-3.x" series (covering "Llama 3.1", "Llama 3.2", and "Llama 3.3" based releases), trained on top of Meta’s "Llama-3.1-8B-Instruct":
 https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
 The model is fine-tuned to improve instruction-following behavior in Norwegian Bokmål and Norwegian Nynorsk, while aiming to preserve strong English performance.
-This model series is an experiment in how far modern open-weight models can be adapted for Norwegian using **only publicly available data**. Although trained at the National Library of Norway, it does **not** include material that is only accessible through legal deposit. It may include public documents (for example governmental reports) that are publicly available and also part of legal deposit collections.
 ---
@@ -94,7 +95,7 @@ This is a research release. For end-user deployments, we recommend careful evalu
 import torch
 from transformers import pipeline
-model_id = "NbAiLab/nb-llama-3.1-8B-Instruct"
 pipe = pipeline(
     task="text-generation",
@@ -198,4 +199,4 @@ Model training and documentation: **Per Egil Kummervold**.
 ## Funding and acknowledgement
-Training was supported by Google’s TPU Research Cloud ("TRC"), which provided Cloud TPUs essential for the computational work.

   - "en"  # English
 tags:
   - "llama"
+  - "notram"
   - "norwegian"
   - "bokmål"
   - "nynorsk"
 library_name: "transformers"
 ---
+## Model Card: "nb-notram-llama-3.1-8b-instruct"
 ### Model overview
+"NbAiLab/nb-notram-llama-3.1-8b-instruct" is part of the "NB-Llama-3.x" series (covering "Llama 3.1", "Llama 3.2", and "Llama 3.3" based releases) and the "NoTraM" line of work, trained on top of Meta’s "Llama-3.1-8B-Instruct":
 https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
 The model is fine-tuned to improve instruction-following behavior in Norwegian Bokmål and Norwegian Nynorsk, while aiming to preserve strong English performance.
+This release is an experiment in how far modern open-weight models can be adapted for Norwegian using **only publicly available data**. Although trained at the National Library of Norway, it does **not** include material that is only accessible through legal deposit. It may include public documents (for example governmental reports) that are publicly available and also part of legal deposit collections.
 ---
 import torch
 from transformers import pipeline
+model_id = "NbAiLab/nb-notram-llama-3.1-8b-instruct"
 pipe = pipeline(
     task="text-generation",
 ## Funding and acknowledgement
+Training was supported by Google’s TPU Research Cloud ("TRC"), which provided Cloud TPUs essential for the computational work.