Update README.md

README.md

@@ -39,360 +39,48 @@ The corpus was compiled by this process:
 4. Since most of that dataset contains only a single dialogue turn, we generated more turns using [Mixtral-8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).
 5. Finally, we translated the resulting dataset into Bokmål and Nynorsk using [NorMistral-7b-warm](https://huggingface.co/norallm/normistral-7b-warm).
 
-## About the base model
-
-NorMistral-7b-warm is a large Norwegian language model initialized from [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and 
-continuously pretrained on a total of 260 billion subword tokens (using six repetitions of open Norwegian texts).
-
-This model is a part of the NORA.LLM family developed in collaboration between [the Language Technology Group at the University of Oslo](https://huggingface.co/ltg), [the High Performance Language Technologies (HPLT) project](https://hplt-project.org/), [the National Library of Norway](https://huggingface.co/NbAiLab), and [the University of Turku](https://huggingface.co/TurkuNLP).
-All the models are pre-trained on the same dataset and with the same tokenizer.
-NorMistral-7b-warm has over 7 billion parameters and is based on [the Mistral architecture](https://huggingface.co/mistralai/Mistral-7B-v0.1).
-
-The NORA.LLM language model family includes (as of now):
-- [**NorMistral-7b-warm**](https://huggingface.co/norallm/normistral-7b-warm) -- an LLM initialized from [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and continuously pretrained on Norwegian data;
-- [**NorMistral-7b-scratch**](https://huggingface.co/norallm/normistral-7b-scratch) -- a Mistral-based LLM pretrained from scratch on Norwegian data;
-- [**NorBLOOM-7b-scratch**](https://huggingface.co/norallm/NorBLOOM-7b-scratch) -- a BLOOM-based LLM pretrained from scratch on Norwegian data.
-
-
-*Disclaimer: This model is pretrained on raw (mostly web-based) textual data.
-It is not finetuned to follow instructions, and it can generate harmful completions after inappropriate user prompts.
-It is primarily intended for research purposes.*
-
-_____
-## Pretraining corpus
-
-The model is pretrained exclusively on publicly available data. We combine the resources from [the public part of the NCC corpus](https://huggingface.co/datasets/NbAiLab/NCC), from [the cleaned HPLT corpus](https://hplt-project.org/datasets/v1.2), and from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX).
-This resulted in over 34B subword tokens of Norwegian (Bokmål or Nynorsk) in total, which amounts to about 26.7B whitespace-separated tokens
-We also augment the corpus with [Starcoder](https://huggingface.co/datasets/vikp/starcoder_filtered); 20% of the 260B tokens are sampled from this code corpus.
-The natural language data is repeated six times to get the pretraining budget of 260B tokens, in accordance with findings from [Muennighoff et al. (2023)](https://neurips.cc/virtual/2023/poster/70706).
-
-_____
-## Model details
-
-**Model Developers:** Language Technology Group at the University of Oslo.
-
-**Variations:** NorMistral is currently published as two 7B variants: one trained entirely from *scratch* and one *warm*-started from the Mistral model.
-
-**Input:** Textual input.
-
-**Output:** Generated text.
-
-**Model Architecture:** NorMistral is an auto-regressive language model that uses an optimized transformer architecture based on the Mistral/Llama language models.
-
-||Training Data|Params|Context Length|Tokens|LR|
-|---|---|---|---|---|---|
-|NorMistral-7b-warm|NCC+HPLT+CulturaX+Starcoder|7B|2k|260B|1.0 x 10<sup>-4</sup>|
-|NorMistral-7b-scratch|NCC+HPLT+CulturaX+Starcoder|7B|2k|260B|3.0 x 10<sup>-4</sup>|
-|NorBLOOM-7b-scratch|NCC+HPLT+CulturaX+Starcoder|7B|2k|260B|1.2 x 10<sup>-4</sup>|
-
-**Tokenizer:** Byte-based BPE tokenizer trained on the same Norwegian corpus as this model. The vocabulary size is 32,768 tokens.
-
-**Training FLOPs** The approximate amount is 1.22e+22 FLOPs; calculated as in [Chowdhery et al. (2022)](https://arxiv.org/abs/2204.02311).
-
-**Model Dates:** The models were pretrained between December 2023 and January 2024.
-
-**Status:** These are only pretrained language models; instruction-finetuned models will follow soon.
-
-**License:** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0)
-
-**Research Paper:** Forthcoming
-
-_____
-## Initial evaluation
-
-*Disclaimer: our model evaluation is an ongoing phase and is not claimed to be exhaustive. We provide our initial evaluation results on standard natural language understanding and generation tasks, and our evaluation design will be extended. 
-The user should perform evaluation for their particular model application scenario, including safety and bias evaluations.*
-
-The perplexity on the heldout [validation set from the Norwegian Colossal Corpus (NCC)](https://huggingface.co/datasets/NbAiLab/NCC) is 7.43 and the final training perplexity is 4.76.
-
-Our initial downstream evaluation is conducted on reading comprehension, sentiment analysis and machine translation tasks using open-source peer-reviewed datasets and benchmarks in native Norwegian.
-We release [our codebase here](https://github.com/ltgoslo/norallm). We compare against other pretrained generative language models that officially support Norwegian: [NB-GPT-J](https://huggingface.co/NbAiLab/nb-gpt-j-6B), [GPT-Sw3 6.7B](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b), [GPT-Sw3 6.7B v2](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2), and [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b); we also include evaluation of [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
-
-
-### Sentiment analysis
-
-[NoReC](https://huggingface.co/datasets/ltg/norec_sentence) ([Øvrelid et al., 2020](https://aclanthology.org/2020.lrec-1.618/)) is a dataset for sentence-level sentiment analysis derived from the Norwegian Review Corpus [(Velldal et al., 2018)](https://aclanthology.org/L18-1661/).
-We use the binary formulation of this task (positive vs. negative).
-
-<details>
-<summary>Method (click to expand)</summary>
-  
-* Evaluation setting: zero-shot and few-shot perplexity-based evaluation.
-* Prompt: ```"Tekst: {text}\nSentiment:{label}"```, where the ```label``` is either "positiv" or "negativ".
-* Few-shot results show the average scores across 5 repetitions
-* Evaluation script: https://github.com/ltgoslo/norallm/blob/main/initial_evaluation/sentiment_analysis.py
-* Performance metric: macro-averaged F1-score.
-
-</details>
-
-<details open>
-<summary>Macro-averaged F1-scores on the sentence-level sentiment analysis task (NoReC)</summary>
-
-|Model|0-shot (macro F1)|1-shot (macro F1)|16-shot (macro F1)|
-|---|---|---|---|
-|NorMistral-7b-warm|60.6|**77.8**|**87.3**|
-|NorMistral-7b-scratch|47.3|62.2|80.1|
-|NorBLOOM-7b|**75.7**|73.8|65.5|
-|NB-GPT-J|48.4|56.5|65.2|
-|GPT-Sw3-6.7B|61.5|72.2|76.5|
-|GPT-Sw3-6.7B-v2|42.4|69.1|83.4|
-|Falcon-7B|53.3|61.6|74.9|
-|Mistral-7B-v0.1|70.2|72.9|84.8|
-
-</details>
-
-
-
-### Reading comprehension
-
-[NorQuAD](https://huggingface.co/datasets/ltg/norquad) ([Ivanova et al., 2023](https://aclanthology.org/2023.nodalida-1.17/)) is a dataset for extractive question answering in Norwegian designed similarly to [SQuAD (Rajpurkar et al., 2016)](https://aclanthology.org/D16-1264/).
-
-<details>
-<summary>Method (click to expand)</summary>
-  
-* Evaluation setting: zero-shot and few-shot settings via natural language generation using the greedy decoding strategy.
-* Prompt: ```"Tittel: {title}\n\nTekst: {text}\n\nSpørsmål: {question}\n\nSvar:{answer}"``` Based on [Brown et al. (2020)](https://arxiv.org/abs/2005.14165).
-* Few-shot results show the average scores across 5 repetitions
-* Evaluation script: https://github.com/ltgoslo/norallm/blob/main/initial_evaluation/norquad.py
-* Performance metrics: macro-averaged F1-score and exact match (EM).
-  
-</details>
-
-<details open>
-<summary>Performance results on the extractive question answering task (NorQuAD)</summary>
-
-|Model|0-shot (F1/EM)|1-shot (F1/EM)|2-shot (F1/EM)|
-|---|---|---|---|
-|NorMistral-7b-warm|**48.6**/**24.8**|63.6/40.0|66.5/43.8|
-|NorMistral-7b-scratch|34.0/15.7|46.5/25.8|48.5/27.8|
-|NorBLOOM-7b|35.0/13.3|47.7/28.0|49.3/30.1|
-|NB-GPT-J|24.4/6.8|32.8/11.6|35.0/12.3|
-|GPT-Sw3-6.7B|46.5/22.0|55.9/32.0|58.1/34.3|
-|GPT-Sw3-6.7B-v2|46.9/22.5|61.1/38.9|66.0/44.5|
-|Falcon-7B|15.8/7.0|27.3/13.9|27.4/13.1|
-|Mistral-7B-v0.1|46.4/22.4|**64.9**/**41.1**|**71.7**/**49.4**|
-
-</details>
-
-
-### Grammatical error correction
-
-[ASK-RAW](https://huggingface.co/datasets/ltg/ask-gec) is dataset for Norwegian grammatical error correction (GEC) created by [Matias Jentoft (2023)](https://www.duo.uio.no/handle/10852/103885).
-
-<details>
-<summary>Method (click to expand)</summary>
-  
-* Evaluation setting: zero-shot and few-shot settings via natural language generation using the greedy decoding strategy.
-* Prompt: ```"Her er eksempler på perfekt korrigering av grammatiske feil:\n\nTekst: {source_text}\nKorreksjon:{target_text}"```
-* Few-shot results show the average scores across 5 repetitions
-* Evaluation script: https://github.com/ltgoslo/norallm/blob/main/initial_evaluation/gec.py
-* Performance metrics: the evaluation metric uses [ERRANT](https://github.com/chrisjbryant/errant/tree/main), which identifies edit-spans and then calculates the F_{0.5} scores between the gold edits and predicted edits. 
-  
-</details>
-
-<details open>
-<summary>Results on [the ASK corpus](https://huggingface.co/datasets/ltg/ask-gec) (ERRANT F_{0.5})</summary>
-
-|Model|0-shot (F0.5)|1-shot (F0.5)|32-shot (F0.5)|
-|---|---|---|---|
-|NorMistral-7b-warm|**40.8**|41.8|48.5|
-|NorMistral-7b-scratch|22.1|28.8|42.1|
-|NorBLOOM-7b|8.7|24.5|32.0|
-|NB-GPT-J|9.1|28.2|30.6|
-|GPT-Sw3-6.7B|30.5|42.9|**50.6**|
-|GPT-Sw3-6.7B-v2|40.6|**43.4**|49.8|
-|Falcon-7B|10.8|12.4|15.5|
-|Mistral-7B-v0.1|26.0|27.4|30.6|
-
-</details>
-
-
-### Machine translation
-
-[Tatoeba](https://huggingface.co/datasets/Helsinki-NLP/tatoeba_mt) [(Tiedemann, 2020)](https://aclanthology.org/2020.wmt-1.139/) is a benchmark for machine translation, which includes hundreds of language pairs. We consider six language pairs (English <-> Bokmål, English <-> Nynorsk, and Bokmål <-> Nynorsk).
-
-<details>
-<summary>Method (click to expand)</summary>
-  
-* Evaluation setting: zero-shot and few-shot settings via natural language generation using the greedy decoding strategy.
-* Prompt: ```"{source_language}: {source_text}\n{target_language}:{target_text}"```, where the ```source_language``` and ```target_language``` are ```Engelsk```, ```Bokmål```, or ```Nynorsk```. Based on [Garcia et al. (2023)](https://arxiv.org/abs/2302.01398).
-* Few-shot results show the average scores across 5 repetitions
-* Evaluation script: https://github.com/ltgoslo/norallm/blob/main/initial_evaluation/machine_translation.py
-* Performance metrics: BLEU ([Papineni et al., 2002](https://aclanthology.org/P02-1040/)) and chrF++ ([Popović, 2015](https://aclanthology.org/W15-3049/)).
-
-</details>
-
-<details open>
-<summary>English → Norwegian Bokmål</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**55.8**/**70.7**|**56.7**/**71.5**|57.7/72.4|
-|NorMistral-7b-scratch|46.4/62.9|50.4/66.3|52.1/67.6|
-|NorBLOOM-7b|37.1/53.6|50.1/65.8|52.0/67.6|
-|NB-GPT-J|8.6/39.1|35.9/64.5|47.2/68.7|
-|GPT-Sw3-6.7B|21.8/55.2|54.5/69.6|**58.6**/**73.2**|
-|GPT-Sw3-6.7B-v2|20.6/53.2|51.2/66.6|58.4/73.0|
-|Falcon-7B|19.1/40.1|20.6/41.8|22.1/43.6|
-|Mistral-7B-v0.1|32.5/51.9|35.4/55.1|36.3/56.0|
-
-
-</details>
-
-<details open>
-<summary>English → Norwegian Nynorsk</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**43.6**/**62.0**|**44.2**/**63.2**|44.3/**63.7**|
-|NorMistral-7b-scratch|38.0/56.9|39.2/57.9|40.7/59.3|
-|NorBLOOM-7b|35.6/54.7|36.6/56.3|38.1/57.4|
-|NB-GPT-J|1.7/14.7|6.3/34.1|35.2/60.4|
-|GPT-Sw3-6.7B|13.4/44.3|43.6/62.5|**44.5**/63.5|
-|GPT-Sw3-6.7B-v2|14.8/45.5|43.7/62.3|44.0/63.6|
-|Falcon-7B|6.4/28.6|8.3/30.5|9.3/32.1|
-|Mistral-7B-v0.1|11.6/35.7|13.5/38.7|15.0/40.0|
-
-
-</details>
-
-
-<details open>
-<summary>Norwegian Bokmål → English</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**56.7**/**70.6**|**57.7**/**71.7**|**58.5**/**72.2**|
-|NorMistral-7b-scratch|48.1/62.9|51.5/66.6|52.6/67.6|
-|NorBLOOM-7b|46.0/61.5|51.3/66.7|51.7/66.9|
-|NB-GPT-J|23.9/55.3|32.3/63.1|48.5/68.7|
-|GPT-Sw3-6.7B|47.9/67.8|52.4/70.6|50.0/70.7|
-|GPT-Sw3-6.7B-v2|38.8/59.6|49.0/68.6|50.7/70.6|
-|Falcon-7B|42.4/58.5|47.3/62.3|48.6/63.3|
-|Mistral-7B-v0.1|53.8/68.2|54.6/69.0|56.9/70.7|
-
-</details>
-
-<details open>
-<summary>Norwegian Nynorsk → English</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**55.1**/**68.4**|**55.5**/**69.5**|56.0/69.8|
-|NorMistral-7b-scratch|47.1/61.9|49.4/64.2|52.3/66.2|
-|NorBLOOM-7b|45.0/59.3|48.3/64.0|49.0/64.7|
-|NB-GPT-J|2.9/19.5|10.1/41.0|44.4/66.9|
-|GPT-Sw3-6.7B|47.8/66.2|49.1/68.1|49.6/69.4|
-|GPT-Sw3-6.7B-v2|46.3/67.5|48.9/69.3|**58.2**/**72.8**|
-|Falcon-7B|21.6/40.6|31.7/47.4|36.6/57.1|
-|Mistral-7B-v0.1|40.7/57.1|46.2/60.7|49.9/63.8|
-
-</details>
-
-
-<details open>
-<summary>Norwegian Bokmål → Norwegian Nynorsk</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**75.8**/**87.5**|74.0/**86.9**|75.3/87.5|
-|NorMistral-7b-scratch|38.0/56.9|39.2/57.9|40.7/59.3|
-|NorBLOOM-7b|71.5/84.4|70.1/84.1|71.9/85.1|
-|NB-GPT-J|6.6/35.5|9.6/41.0|26.0/64.7|
-|GPT-Sw3-6.7B|63.6/82.8|74.7/86.0|75.8/86.9|
-|GPT-Sw3-6.7B-v2|57.5/81.1|**75.3**/86.7|**76.7**/**87.6**|
-|Falcon-7B|28.7/59.2|29.8/60.8|32.1/62.3|
-|Mistral-7B-v0.1|32.0/62.2|32.9/62.6|35.2/63.9|
-
-
-</details>
-
-<details open>
-<summary>Norwegian Nynorsk → Norwegian Bokmål</summary>
-
-|Model|0-shot (BLEU/chrF++)|1-shot (BLEU/chrF++)|5-shot (BLEU/chrF++)|
-|---|---|---|---|
-|NorMistral-7b-warm|**88.1**/**93.6**|**89.2**/**94.3**|**89.3**/**94.6**|
-|NorMistral-7b-scratch|85.1/91.4|86.6/92.4|87.4/93.0|
-|NorBLOOM-7b|78.7/88.5|84.2/90.7|87.4/93.0|
-|NB-GPT-J|2.7/18.5|6.9/35.6|52.9/84.3|
-|GPT-Sw3-6.7B|652.3/82.4|86.1/92.5|87.8/93.6|
-|GPT-Sw3-6.7B-v2|72.0/88.6|86.1/92.5|88.2/93.9|
-|Falcon-7B|36.7/61.6|38.3/63.5|45.8/68.1|
-|Mistral-7B-v0.1|57.0/74.8|59.9/77.5|62.6/79.1|
-
-</details>
-
-
-
-_____
-## Hardware and Software
-
-**Training Factors:** The models were pretrained using the Megatron-DeepSpeed library on [the LUMI cluster in Finland](https://lumi-supercomputer.eu/).
-
-**Carbon Footprint:** Pretraining one model took approximately 70k GPU hours of computation on AMD MI250X GPUs (assuming 2 GPUs per one AMD MI250X device), each of which draws 500W.
-LUMI is [one of the most eco-efficient data centers in the world](https://www.lumi-supercomputer.eu/sustainable-future/), and its energy consumption is covered 100% with renewable electricity.
+## Prompt format
 
+NorMistral uses ChatML-like format for structuring the (multi-turn) conversations. An example of a prompt in this format looks like the following (notice the special `<|im_start|>` and `<|im_end|>` tokens).
 
+```
+<|im_start|> user
+Hva er hovedstaden i Norge?<|im_end|>
+<|im_start|> assistant
+Hovedstaden i Norge er Oslo. Denne byen ligger i den sørøstlige delen av landet, ved Oslofjorden. Oslo er en av de raskest voksende byene i Europa, og den er kjent for sin rike historie, kultur og moderne arkitektur. Noen populære turistattraksjoner i Oslo inkluderer Vigelandsparken, som viser mer enn 200 skulpturer laget av den berømte norske skulptøren Gustav Vigeland, og det kongelige slott, som er den offisielle residensen til Norges kongefamilie. Oslo er også hjemsted for mange museer, gallerier og teatre, samt mange restauranter og barer som tilbyr et bredt utvalg av kulinariske og kulturelle opplevelser.<|im_end|>
+<|im_start|> user
+Gi meg en liste over de beste stedene å besøke i hovedstaden
+<|im_start|> assistant
 
-_____
-## Example usage
+```
 
-Let's try to use this model for English-to-Norwegian machine translation using simple zero-shot prompting:
+This prompt-format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) in the NorMistral's tokens, so it can be easily applied by calling the
+`tokenizer.apply_chat_template()` method:
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# First, we will have to import the tokenizer and the language model
-tokenizer = AutoTokenizer.from_pretrained("norallm/normistral-7b-warm")
-model = AutoModelForCausalLM.from_pretrained("norallm/normistral-7b-warm").cuda().eval()
-
-# Now we will define the zero-shot prompt template
-prompt = """Engelsk: {0}
-Bokmål:"""
-
-# A function that will take care of generating the output
-@torch.no_grad()
-def generate(text):
-    text = prompt.format(text)
-    input_ids = tokenizer(text, return_tensors='pt').input_ids.cuda()
-    prediction = model.generate(
-        input_ids,
-        max_new_tokens=64,
-        do_sample=False,
-        eos_token_id=tokenizer('\n').input_ids
-    )
-    return tokenizer.decode(prediction[0, input_ids.size(1):]).strip()
-
-# Now you can simply call the generate function with an English text you want to translate:
-generate("I'm super excited about this Norwegian NORA model! Can it translate these sentences?")
-# > this should output: 'Jeg er super spent på denne norske NORA modellen! Kan den oversette disse setningene?'
+messages = [
+    {"role": "user", "content": "Hva er hovedstaden i Norge?"},
+    {"role": "assistant", "content": "Hovedstaden i Norge er Oslo. Denne byen ligger i den sørøstlige delen av landet, ved Oslofjorden. Oslo er en av de raskest voksende byene i Europa, og den er kjent for sin rike historie, kultur og moderne arkitektur. Noen populære turistattraksjoner i Oslo inkluderer Vigelandsparken, som viser mer enn 200 skulpturer laget av den berømte norske skulptøren Gustav Vigeland, og det kongelige slott, som er den offisielle residensen til Norges kongefamilie. Oslo er også hjemsted for mange museer, gallerier og teatre, samt mange restauranter og barer som tilbyr et bredt utvalg av kulinariske og kulturelle opplevelser."}
+    {"role": "user", "content": "Gi meg en liste over de beste stedene å besøke i hovedstaden"}
+]
+gen_input = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+model.generate(**gen_input)
 ```
 
-## Example usage on a GPU with ~16GB VRAM (try for yourself [in Google Colab](https://colab.research.google.com/drive/1AQgJ8lN-SNOqkUKj4xpQI5rr0R7V2Xzy?usp=sharing))
-Install bitsandbytes if you want to load in 8bit
+When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
+that the model continues with an assistant response.
 
-```bash
-pip install bitsandbytes
-pip install accelerate
-```
 
+## About the base model
 
-```python
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
+NorMistral-7b-warm is a large Norwegian language model initialized from [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and 
+continuously pretrained on a total of 260 billion subword tokens (using six repetitions of open Norwegian texts).
 
-tokenizer = AutoTokenizer.from_pretrained(
-    "norallm/normistral-7b-warm"
-)
+This model is a part of the NORA.LLM family developed in collaboration between [the Language Technology Group at the University of Oslo](https://huggingface.co/ltg), [the High Performance Language Technologies (HPLT) project](https://hplt-project.org/), [the National Library of Norway](https://huggingface.co/NbAiLab), and [the University of Turku](https://huggingface.co/TurkuNLP).
+All the models are pre-trained on the same dataset and with the same tokenizer.
+NorMistral-7b-warm has over 7 billion parameters and is based on [the Mistral architecture](https://huggingface.co/mistralai/Mistral-7B-v0.1).
 
-# This setup needs about 8gb VRAM
-# Setting `load_in_8bit=False` -> 15gb VRAM
-# Using `torch.float32` and `load_in_8bit=False` -> 21gb VRAM
-model = AutoModelForCausalLM.from_pretrained(
-    "norallm/normistral-7b-warm",
-    device_map='auto',
-    load_in_8bit=True,
-    torch_dtype=torch.bfloat16
-)
-```
+The NORA.LLM language model family includes (as of now):
+- [**NorMistral-7b-warm**](https://huggingface.co/norallm/normistral-7b-warm) -- an LLM initialized from [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) and continuously pretrained on Norwegian data;
+- [**NorMistral-7b-scratch**](https://huggingface.co/norallm/normistral-7b-scratch) -- a Mistral-based LLM pretrained from scratch on Norwegian data;
+- [**NorBLOOM-7b-scratch**](https://huggingface.co/norallm/NorBLOOM-7b-scratch) -- a BLOOM-based LLM pretrained from scratch on Norwegian data.