NbAiLab/borealis-1b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: NbAiLab/borealis-1b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-14 04:15:17 +08:00
commit f0bb63974b
20 changed files with 899 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
.gitattributes vendored Normal file
View File

@@ -0,0 +1,40 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
LICENSE_FAQ.pdf filter=lfs diff=lfs merge=lfs -text
borealis.png filter=lfs diff=lfs merge=lfs -text
borealis_evals_202605.png filter=lfs diff=lfs merge=lfs -text
Model_Documentation_Form.pdf filter=lfs diff=lfs merge=lfs -text

180
LICENSE Normal file
View File

@@ -0,0 +1,180 @@
NB-License
Version 1.0, June 2026
https://ai.nb.no/license/
This license (henceforth: NB-license) establishes terms and conditions for use
of Borealis models with the following copyright notice: Borealis Copyright 2026
Nasjonalbiblioteket.
This model is a fine-tuned derivative of Gemma 3, licensed under the Gemma Terms
of Use. The original model is available from Google at
https://deepmind.google/models/gemma/gemma-3/. Modifications, fine-tuning, and
subsequent derivative works are distributed under the NB-license. The original
Gemma Terms of Use notices, disclaimers, attribution, and use restrictions
remain fully intact and are provided at https://ai.google.dev/gemma/terms. The
additional usage restrictions apply only to our derivative work.
1. Definitions.
- "License" means the terms and conditions for use, reproduction, and
Distribution as defined in this document.
- "Licensor" means the copyright owner or entity authorized by the copyright
owner that is granting the License, including the persons or entities that may
have rights in the Model and/or distributing the Model.
- "You" (or "Your") means an individual or Legal Entity exercising permissions
granted by this License and/or making use of the Model for whichever purpose and
in any field of use, including usage of the Model in an end-use application -
e.g. chatbot, translator, image generator.
- "Third Parties" means individuals or legal entities that are not under common
control with Licensor or You.
- "Data" means a collection of information and/or content extracted from the
dataset used with the Model, including to train, pretrain, or otherwise evaluate
the Model. The Data is not licensed under this License.
- "Output" means the results of operating a Model as embodied in informational
content resulting therefrom.
- "Model" means any accompanying machine-learning based assemblies (including
checkpoints), consisting of learnt weights, parameters (including optimizer
states), corresponding to the model architecture as embodied in the
Complementary Material, that have been trained or tuned, in whole or in part on
the Data, using the Complementary Material.
- "Derivatives of the Model" means all modifications to the Model, works based
on the Model, or any other model which is created or initialized by transfer of
patterns of the weights, parameters, activations or output of the Model, to the
other model, in order to cause the other model to perform similarly to the
Model, including - but not limited to - distillation methods entailing the use
of intermediate data representations or methods based on the generation of
synthetic data by the Model for training the other model.
- "Complementary Material" means the accompanying source code and scripts used
to define, run, load, benchmark or evaluate the Model, and used to prepare data
for training or evaluation, if any. This includes any accompanying
documentation, tutorials, examples, etc, if any.
- "Distribution" means any transmission, reproduction, publication or other
sharing of the Model or Derivatives of the Model to a third party, including
providing the Model as a hosted service made available by electronic or other
remote means - e.g. API-based or web access.
- “Use” includes accessing and utilizing a Model or Derivates of a Model, which
may also include creating content, fine-tuning, updating, running, training,
evaluating and/or re-parametrizing such Model or Derivates of a Model.
- "Contribution" means any work of authorship, including the original version of
the Model and any modifications or additions to that Model or Derivatives of the
Model thereof, that is intentionally submitted to Licensor for inclusion in the
Model.
- "Contributor" means Licensor and any individual or Legal Entity on behalf of
whom a Contribution has been received by Licensor and subsequently incorporated
within the Model.
2. Grant of License.
Subject to the terms and conditions of this License, each Contributor hereby
grants to You a time-unlimited, worldwide, non-exclusive, no-charge, royalty-
free license to use, make, have made, reproduce, prepare derivatives of the
model, publicly display, publicly perform, sublicense, offer to sell, sell,
import and otherwise transfer or distribute the model and derivatives of the
model.
3. Redistribution
You may reproduce and distribute copies of the model or derivatives of the model
in any medium, with or without modifications, provided that You meet the
following conditions: (a) You must give any other recipients of the model or
derivatives of the model a copy of this License; and (b) You must retain all
copyright notices in any redistribution of the model or derivatives of the
model, excluding those notices that do not pertain to any part of a derivative
of the model; and (c) You must include the use-based restrictions in section 4
as a condition precedent to effect any type of legal agreement (e.g. a license)
governing the use and/or distribution of the model or its Derivatives, and give
such notice to any subsequent Third Party recipients;
4. Use-based Restrictions.
You can only use the Model in compliance with the following conditions:
(a) You must comply with applicable laws and regulations.
(b) You must not use the model to intentionally recreate material from the
training data, whether protected by intellectual property rights or as personal
data
(c) Neither the name of the National library nor the names of creators or
publishers of training data may be used to endorse or promote products derived
from this model without specific prior written permission.
(d) You must not use the Model or its outputs, to provide end-user services
whose primary purpose is to summarize, restate, copy, or otherwise replace
services for access to the press publications licensed as training data, unless you have a separate agreement with the
copyright holders. This includes, but is not limited to, services that provide
users with functional substitutes for access to the original press content.
5. Outputs.
Except as set forth herein, Licensor claims no rights in the Output You generate
with a model. You are accountable for the Output You generate and its subsequent
uses. No use of the Output may contravene any provision as stated in this
License, hereunder section 4 on use-based restrictions.
6. Disclaimer of Warranty.
Unless required by applicable law or agreed to in writing, Licensor provides the
Work (and each Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
including, without limitation, any warranties or conditions of TITLE, NON-
INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are
solely responsible for determining the appropriateness of using or
redistributing the Work and assume any risks associated with Your exercise of
permissions under this License. The Licensor makes no representations or
warranties that the Model or its Output will be free from factual inaccuracies,
biases, or potential misinterpretation of the underlying training data. You are
solely responsible for ensuring that any use of the Model adheres to applicable
legal and ethical standards.
7. Limitation of Liability.
In no event and under no legal theory, whether in tort (including negligence),
contract, or otherwise, unless required by applicable law (such as deliberate
and grossly negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special, incidental,
or consequential damages of any character arising as a result of this License or
out of the use or inability to use the Work (including but not limited to
damages for loss of goodwill, work stoppage, computer failure or malfunction, or
any and all other commercial damages or losses), even if such Contributor has
been advised of the possibility of such damages.
8. Accepting Warranty or Additional Liability.
While redistributing the Work or Derivative Works thereof, You may choose to
offer, and charge a fee for, acceptance of support, warranty, indemnity, or
other liability obligations and/or rights consistent with this License. However,
in accepting such obligations, You may act only on Your own behalf and on Your
sole responsibility, not on behalf of any other Contributor, and only if You
agree to indemnify, defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason of your
accepting any such warranty or additional liability.
9. Term and Termination.
The term of this Agreement will commence upon your acceptance of this Agreement
and will continue in full force and effect until terminated in accordance with
the terms and conditions herein. Licensor may terminate this Agreement if you
are in breach of any term or condition of this Agreement. Upon termination of
this Agreement, you shall cease use of the licensed model. Section 7 shall
survive the termination of this Agreement. Termination of the agreement does not
affect your continued rights to use parts of the model the licensed model was
based on (if warm trained) under its original license.
10. Governing Law and Jurisdiction.
This Agreement will be governed and construed under the laws of Norway. The Oslo
District Court shall have exclusive jurisdiction of any dispute arising out of
this Agreement.

3
LICENSE_FAQ.pdf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4a87118b0b0c1e2d5a06b27bb4b56517d4d62b2b74860f77b8ac2d601224840
size 140945

3
Model_Documentation_Form.pdf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:89919c8ec2f2d5c700c9afbdfca21cd3dfaa15aee0a305e13b399ed058766cf3
size 335301

248
README.md Normal file
View File

@@ -0,0 +1,248 @@
---
license: other
datasets:
- NbAiLab/aurora-sft
language:
- 'no'
- nb
- nn
base_model:
- google/gemma-3-1b-it
pipeline_tag: text-generation
library_name: transformers
tags:
- conversational
- instruct
- borealis
- gemma3_text
- norwegian
- norwegian-bokmal
- norwegian-nynorsk
- full-release
---
![Borealis](./borealis.png)
# Borealis 1B
## Model Summary
**NbAiLab/borealis-1b** is a **1B-parameter** instruction-tuned **full release** model in the Borealis family from the National Library of Norway (Nasjonalbiblioteket, NB).
This is the first Borealis release to incorporate data made available under the agreement between rights-holder organizations in Norway and the Norwegian government. To date, only a limited subset of the material has been used, specifically to teach the model how to generate news article titles and ingress texts. Models with the suffix `-open`, do not include any material from the agreement.
All Borealis released models are based on the **Gemma 3** family. This model is based on [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it), and fine-tuned for Norwegian-centric instruction following.
### Sizes
| Size | Full release | Open release |
|---:|---|---|
| 27B | [NbAiLab/borealis-27b](https://huggingface.co/NbAiLab/borealis-27b) | [NbAiLab/borealis-open-27b](https://huggingface.co/NbAiLab/borealis-open-27b) |
| 12B | [NbAiLab/borealis-12b](https://huggingface.co/NbAiLab/borealis-12b) | [NbAiLab/borealis-open-12b](https://huggingface.co/NbAiLab/borealis-open-12b) |
| 4B | [NbAiLab/borealis-4b](https://huggingface.co/NbAiLab/borealis-4b) | [NbAiLab/borealis-open-4b](https://huggingface.co/NbAiLab/borealis-open-4b) |
| 1B | [NbAiLab/borealis-1b](https://huggingface.co/NbAiLab/borealis-1b) | [NbAiLab/borealis-open-1b](https://huggingface.co/NbAiLab/borealis-open-1b) |
| 270M | [NbAiLab/borealis-270m](https://huggingface.co/NbAiLab/borealis-270m) | [NbAiLab/borealis-open-270m](https://huggingface.co/NbAiLab/borealis-open-270m) |
## Training Data
Supervised fine-tuning (SFT) uses instruction data prepared by the National Library of Norway for Norwegian-centric assistant behavior, writing, summarization, question answering, and related tasks.
The SFT dataset for this model is [NbAiLab/aurora-sft](https://huggingface.co/datasets/NbAiLab/aurora-sft). [NbAiLab/aurora-sft-open](https://huggingface.co/datasets/NbAiLab/aurora-sft-open) is the open version of the SFT dataset. The only difference between [NbAiLab/aurora-sft-open](https://huggingface.co/datasets/NbAiLab/aurora-sft-open) and [NbAiLab/aurora-sft](https://huggingface.co/datasets/NbAiLab/aurora-sft) is the addition of 10k tasks derived from copyright-protected newspapers material.
The Norwegian government has entered into an agreement, through the National Library of Norway, to access copyrighted press material via Kopinor on behalf of the Norwegian Media Businesses' Association (MBL), enabling the lawful training, development, maintenance, and public release of Norwegian language models. The agreement covers copyright-protected press publications published in Norway up to one year from the date of publication of the model, effectively creating a rolling cutoff date rather than a fixed historical cutoff. For this release, the cutoff date is January 1, 2025.
## Evaluation
<figure>
<img src="./borealis_evals_202605.png" alt="Borealis evaluation results">
<figcaption>Borealis evaluation results on selected tasks (best score among {0-5}-shot).</figcaption>
</figure>
We evaluate Borealis with NorEval, MMLU-English, and nb-gpt-bench, our own evaluation suite, which will be published and described in an upcoming paper. Despite using only around 10k newspaper-derived tasks from the abovementioned agreement, we observe a slight performance increase in some key metrics. We hope to further increase the difference by incorporating proper pre-training on the newspaper material.
## Safety and Alignment
The Borealis family of models are aligned for safety using prompt baking and weighted merging of SFT and aligned models. The goal of this process is to balance model quality, usefulness, and safer behavior.
As with all generative models, outputs can still be incorrect, biased, harmful, or inappropriate. Do not use the model for safety-critical or high-stakes applications without additional evaluation and safeguards.
### Prompt Baking
To align the Borealis models, we employ *prompt baking*, a procedure that distills the behavior induced by a system prompt directly into the model weights using [`bakery`](https://github.com/marksverdhei/bakery). Specifically, we train a LoRA adapter to minimize the KL-divergence between two model distributions: Borealis conditioned on the system prompt, and the same base model augmented with the LoRA adapter but evaluated without the system prompt in context. This objective encourages the adapter to reproduce the behavioral effects of the prompt without requiring the prompt to be present at inference time.
To reduce degradation on downstream tasks and preserve general model utility, we merge the resulting prompt adapter into the base model using a scaling factor of `0.25`, which we found to provide the best empirical trade-off.
## Intended Use
- Norwegian-centric assistant-style tasks, including drafting, summarization, Q&A, and light reasoning (this is not a reasoning model).
- Assessment and improvement of Norwegian writing style and quality.
- Evaluation of behavior and language coverage for Norwegian, Bokmål, and Nynorsk.
## Usage
This repository contains the Transformers/safetensors version of the model. The
examples below use `NbAiLab/borealis-1b` as the model id; replace it with
another Borealis repo id if needed.
### Transformers
Use the regular causal language-model interface:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "NbAiLab/borealis-1b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="auto",
torch_dtype=torch.bfloat16,
)
messages = [
{
"role": "user",
"content": "Skriv et kort sammendrag av hva Nasjonalbiblioteket gjør.",
}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
new_tokens = outputs[0, inputs["input_ids"].shape[-1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=True))
```
### vLLM
Serve the model with vLLM's OpenAI-compatible server:
```bash
vllm serve NbAiLab/borealis-1b --served-model-name borealis-1b
```
Then call the local chat completions endpoint:
```bash
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "borealis-1b",
"messages": [
{
"role": "user",
"content": "Skriv tre korte punkter om norsk språkteknologi."
}
],
"max_tokens": 256
}'
```
Large models may require tensor parallelism or reduced memory settings depending
on the available GPU memory.
### llama.cpp
llama.cpp uses GGUF files, not the safetensors files in this repository. When
the planned GGUF companion repository is available, you can run it directly from
the Hub:
```bash
llama-server -hf NbAiLab/borealis-1b-gguf --port 8080
```
Or download a GGUF file and run it locally:
```bash
llama-cli -m borealis-1b.gguf \
-p "Skriv et kort sammendrag av hva Nasjonalbiblioteket gjør." \
-n 256
```
### Ollama
Ollama also requires a GGUF model. Once the GGUF companion repository is
available, you can run it from Hugging Face:
```bash
ollama run hf.co/NbAiLab/borealis-1b-gguf
```
For a local GGUF file, create a minimal `Modelfile`:
```text
FROM ./borealis-1b.gguf
```
Then create and run the local Ollama model:
```bash
ollama create borealis-1b -f Modelfile
ollama run borealis-1b "Skriv tre korte punkter om norsk språkteknologi."
```
## Limitations
- The model may hallucinate or produce incorrect information.
- Safety alignment reduces but does not eliminate harmful or inappropriate outputs.
- Performance outside Norwegian and English use cases has not been fully characterized.
## EU AI Act
The model is a fine-tune of Gemma 3. Using Gemma 3 27B as a conservative upper-bound reference, the original Gemma 3 27B training compute is estimated at approximately 2.1-2.3 x 10^24 FLOPs, based on the disclosed 14T training-token budget and the 27B parameter scale. The fine-tuning run used approximately 3.4 x 10^20 FLOPs, or about 0.015% of the estimated original training compute. This is substantially below the European Commission's indicative one-third threshold for treating a downstream modification as a significant modification that would make the modifier the provider of the modified General Purpose AI (GPAI) model.
On that basis, the fine-tuning activity is preliminarily assessed as not constituting a substantial modification for the purpose of becoming the provider of a new modified GPAI model under the compute-based criterion. However, the resulting model remains derived from a generative general-purpose AI model and may still be subject to downstream AI-system obligations under the EU AI Act.
For additional model-level documentation, see the [Model Documentation Form](./Model_Documentation_Form.pdf).
## License
The license of this model is an adaptation of the Apache 2.0 license with additional use-based restrictions. In particular, users of the model are required to refrain from intentionally using the model to recreate data the model has been trained on. The license also requires users not to use the model or its output to provide end-user services whose primary purpose is to give access to licensed press publications in the training data.
For more information, see the [LICENSE](./LICENSE) and the [License FAQ](./LICENSE_FAQ.pdf).
## Authenticity
This model release is signed by the National Library of Norway. The signed manifest in `signing/SHA256SUMS` covers the model-runtime artifacts, including model weights, configuration, tokenizer files, and chat template.
To verify model authenticity and file integrity after downloading the repository, run:
```bash
bash signing/verify.sh
```
For more verification instructions, see [ai.nb.no/verify](https://ai.nb.no/verify).
## Weights
This repository contains the Transformers (safetensors) release of **NbAiLab/borealis-1b**.
Companion formats:
- GGUF: [NbAiLab/borealis-1b-gguf](https://huggingface.co/NbAiLab/borealis-1b-gguf)
- MLX: [NbAiLab/borealis-1b-mlx](https://huggingface.co/NbAiLab/borealis-1b-mlx)
- MLX 8-bit: [NbAiLab/borealis-1b-mlx-8bits](https://huggingface.co/NbAiLab/borealis-1b-mlx-8bits)
## Citation and Contributors
The Borealis family of models is a joint effort of multiple teams at the National Library of Norway. Led by Javier de la Rosa ([@versae](https://huggingface.co/versae)), key contributors include (in alphabetical order) Rolv-Arild Braaten, Magnus Breder Birkenes, Lucas Charpentier, Pawel Cyrta, Tita Enstad, Markus Sverdvik Heiervang, Arne Martinus Lindstad, Marthe Løken Midtgaard, Marie Roald, Marie Røsok, Thea Tollersrud, and Angelina Zanardi. Olaus Ingskog Bergstrøm contributed with legal advice. And Yngvil Beyer, Svein Arne Brygfjeld, and Wilfred Østgulen helped with strategic oversight.
A tecnical report will be released soon.
## Acknowledgements
Thanks to the Gemma team at Google for releasing Gemma 3, and to everyone contributing to the Norwegian language technology ecosystem.
## Disclaimer
The models published in this repository are intended for a generalist purpose and are available to third parties. These models may have bias and/or any other undesirable distortions. When third parties, deploy or provide systems and/or services to other parties using any of these models (or using systems based on these models) or become users of the models, they should note that it is their responsibility to mitigate the risks arising from their use and, in any event, to comply with applicable regulations, including regulations regarding the use of artificial intelligence. In no event shall the owner of the models (The National Library of Norway) be liable for any results arising from the use made by third parties of these models.
## Contact
For feedback, technical concerns, or collaboration inquiries, please contact <a rel="noopener nofollow" href="mailto:ailab@nb.no">ailab@nb.no</a>.

3
borealis.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e6d03db57f4f12b359910620c4ba80b70f4fe0711d8125600434663137eb528
size 778162

3
borealis_evals_202605.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f2b6e74b343ba10c6ee5e8a7913a70d8b8e5335a4138ef583ee2baeb9e07655
size 130041

47
chat_template.jinja Normal file
View File

@@ -0,0 +1,47 @@
{{ bos_token }}
{%- if messages[0]['role'] == 'system' -%}
{%- if messages[0]['content'] is string -%}
{%- set first_user_prefix = messages[0]['content'] + '
' -%}
{%- else -%}
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
' -%}
{%- endif -%}
{%- set loop_messages = messages[1:] -%}
{%- else -%}
{%- set first_user_prefix = "" -%}
{%- set loop_messages = messages -%}
{%- endif -%}
{%- for message in loop_messages -%}
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
{%- endif -%}
{%- if (message['role'] == 'assistant') -%}
{%- set role = "model" -%}
{%- else -%}
{%- set role = message['role'] -%}
{%- endif -%}
{{ '<start_of_turn>' + role + '
' + (first_user_prefix if loop.first else "") }}
{%- if message['content'] is string -%}
{{ message['content'] | trim }}
{%- elif message['content'] is iterable -%}
{%- for item in message['content'] -%}
{%- if item['type'] == 'image' -%}
{{ '<start_of_image>' }}
{%- elif item['type'] == 'text' -%}
{{ item['text'] | trim }}
{%- endif -%}
{%- endfor -%}
{%- else -%}
{{ raise_exception("Invalid content type") }}
{%- endif -%}
{{ '<end_of_turn>
' }}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{'<start_of_turn>model
'}}
{%- endif -%}

72
config.json Normal file
View File

@@ -0,0 +1,72 @@
{
"_sliding_window_pattern": 6,
"architectures": [
"Gemma3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"dtype": "bfloat16",
"eos_token_id": 106,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 6912,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 4,
"num_hidden_layers": 26,
"num_key_value_heads": 1,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000,
"rope_type": "default"
}
},
"sliding_window": 512,
"sliding_window_pattern": 6,
"tie_word_embeddings": true,
"transformers_version": "5.8.0",
"use_bidirectional_attention": false,
"use_cache": false,
"vocab_size": 262144
}

14
generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 2,
"cache_implementation": "hybrid",
"do_sample": true,
"eos_token_id": [
106,
1,
106
],
"pad_token_id": 0,
"top_k": 64,
"top_p": 0.95,
"transformers_version": "5.8.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cc44cae80af9457f9e6d22346d5c6c9598ff2cbdf2f61ee5aba58659130bf8a6
size 1999811208

8
signing/SHA256SUMS Normal file
View File

@@ -0,0 +1,8 @@
7de1c58e208eda46e9c7f86397df37ec49883aeece39fb961e0a6b24088dd3c4 chat_template.jinja
f3ec312ba0a893f7adf275d4203edaa4348d74bd6047a43b4812b1ff787b19c6 config.json
d658664f05444ad13f0b7f1298cea34e5b745583f0c720d74531c49549fa1fa1 generation_config.json
cc44cae80af9457f9e6d22346d5c6c9598ff2cbdf2f61ee5aba58659130bf8a6 model.safetensors
2f7b0adf4fb469770bb1490e3e35df87b1dc578246c5e7e6fc76ecf33213a397 special_tokens_map.json
daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726 tokenizer.json
1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c tokenizer.model
d9aedd7a33a5aff2d3b8426eb18aed48e701213b0945564537ef6cd8844b9150 tokenizer_config.json

BIN
signing/SHA256SUMS.sig Normal file
View File

Binary file not shown.

72
signing/ca-chain.pem Normal file
View File

@@ -0,0 +1,72 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

39
signing/cert.pem Normal file
View File

@@ -0,0 +1,39 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

98
signing/verify.sh Normal file
View File

@@ -0,0 +1,98 @@
#!/bin/bash
#
# Verify the integrity and authenticity of this model release.
#
# Usage: bash signing/verify.sh
#
# This script verifies:
# 1. The signing certificate is issued by a trusted CA
# 2. The SHA256SUMS manifest was signed by Nasjonalbiblioteket
# 3. All file checksums match the manifest
#
set -euo pipefail
RED='\033[0;31m'
GREEN='\033[0;32m'
NC='\033[0m'
pass() { echo -e "${GREEN}[PASS]${NC} $*"; }
fail() { echo -e "${RED}[FAIL]${NC} $*" >&2; }
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
MODEL_DIR="$(dirname "$SCRIPT_DIR")"
SIGNING_DIR="$SCRIPT_DIR"
cd "$MODEL_DIR"
errors=0
# Check required files exist
for f in "$SIGNING_DIR/SHA256SUMS" "$SIGNING_DIR/SHA256SUMS.sig" \
"$SIGNING_DIR/cert.pem" "$SIGNING_DIR/ca-chain.pem"; do
if [[ ! -f "$f" ]]; then
fail "Missing file: $f"
errors=$((errors + 1))
fi
done
if [[ $errors -gt 0 ]]; then
echo ""
fail "Required signing files are missing. Cannot verify."
exit 1
fi
echo "=== Nasjonalbiblioteket Model Verification ==="
echo ""
# Show certificate info
echo "Certificate subject:"
openssl x509 -in "$SIGNING_DIR/cert.pem" -subject -noout 2>/dev/null | sed 's/^subject=/ /'
echo "Certificate issuer:"
openssl x509 -in "$SIGNING_DIR/cert.pem" -issuer -noout 2>/dev/null | sed 's/^issuer=/ /'
echo "Certificate fingerprint (SHA-256):"
openssl x509 -in "$SIGNING_DIR/cert.pem" -fingerprint -sha256 -noout 2>/dev/null | sed 's/^.*=/ /'
echo ""
# 1. Verify certificate chain
echo "--- Step 1: Verify certificate chain ---"
if openssl verify -CAfile "$SIGNING_DIR/ca-chain.pem" "$SIGNING_DIR/cert.pem" > /dev/null 2>&1; then
pass "Certificate chain is valid."
else
fail "Certificate chain verification failed!"
errors=$((errors + 1))
fi
# 2. Verify signature
echo "--- Step 2: Verify manifest signature ---"
PUBKEY=$(mktemp)
trap "rm -f '$PUBKEY'" EXIT
openssl x509 -in "$SIGNING_DIR/cert.pem" -pubkey -noout > "$PUBKEY" 2>/dev/null
if openssl dgst -sha256 -verify "$PUBKEY" \
-signature "$SIGNING_DIR/SHA256SUMS.sig" \
"$SIGNING_DIR/SHA256SUMS" > /dev/null 2>&1; then
pass "Manifest signature is valid."
else
fail "Manifest signature verification failed!"
errors=$((errors + 1))
fi
# 3. Verify file checksums
echo "--- Step 3: Verify file checksums ---"
if sha256sum -c "$SIGNING_DIR/SHA256SUMS" 2>/dev/null; then
pass "All file checksums match."
else
fail "One or more file checksums do not match!"
errors=$((errors + 1))
fi
# Summary
echo ""
if [[ $errors -eq 0 ]]; then
echo -e "${GREEN}✅ Verification successful. All files are authentic and unmodified.${NC}"
exit 0
else
echo -e "${RED}❌ Verification failed with $errors error(s).${NC}"
exit 1
fi

33
special_tokens_map.json Normal file
View File

@@ -0,0 +1,33 @@
{
"boi_token": "<start_of_image>",
"bos_token": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eoi_token": "<end_of_image>",
"eos_token": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"image_token": "<image_soft_token>",
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
size 33384567

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
size 4689074

27
tokenizer_config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"backend": "tokenizers",
"boi_token": "<start_of_image>",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eoi_token": "<end_of_image>",
"eos_token": "<end_of_turn>",
"image_token": "<image_soft_token>",
"is_local": false,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"model_specific_special_tokens": {
"boi_token": "<start_of_image>",
"eoi_token": "<end_of_image>",
"image_token": "<image_soft_token>"
},
"pad_token": "<pad>",
"padding_side": "right",
"processor_class": "Gemma3Processor",
"sp_model_kwargs": null,
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}