---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---

# Llama Gaan 2 7B Chat HF Dutch

<!-- Provide a quick summary of what the model is/does. -->

This model is a finetuned version of [LLAMA 2 7B Chat](https://huggingface.co/daryl149/llama-2-7b-chat-hf) aiming for Dutch language support 🇳🇱.
Courtesy of [Mirage Studio](https://www.mirage-studio.io), home of MirageGPT: the private ChatGPT alternative.

[Sign up for the Generative AI NL meetup group while you're here!](https://www.meetup.com/generative-ai-nl/events/295248015/)
[![fancy AI banner](https://drive.google.com/uc?export=view&id=1OweCcQgtJ-VSFjT0IVFlNy5aQM3yZpsx 'Generative AI NL Meetup')](https://www.meetup.com/generative-ai-nl/)

## Model Details
Epoch 5 checkpoint of llama-2-7b-chat-hf, finetuned to speak Dutch. [Find Epoch 1 here for completeness' sake, it's probably worse though.](https://huggingface.co/Mirage-Studio/llama-gaan-2-7b-chat-hf-dutch)


### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** Mirage Studio
- **Model type:** Llama chat
- **Language(s) (NLP):** Dutch
- **License:** [Llama-2 License](https://github.com/facebookresearch/llama/blob/main/LICENSE) 
- **Finetuned from model:** daryl149/llama-2-7b-chat-hf

### Prompt template

```
<s>[INST] <<SYS>>
System prompt
<</SYS>>

User prompt [/INST] Model answer </s>
```

To continue a conversation

```
[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

{prompt} [/INST] {model_reply} [INST] {prompt} [/INST]
```
**N.B.** Set your pad_token_id=18610 in your generator, otherwise it returns gibberish.

### Example usage
An example question you can ask:

Q: Kun je aangeven wat het belang van privacy is voor bedrijven?

A: Het belang van privacy voor bedrijven is dat ze hun klanten moeten beschermen tegen onverhoopt gebruik van persoonlijke gegevens die kunnen leiden tot verlies van privacy, strafrechtelijke problemen of reputatieschade. Bedrijven hebben de plicht om hun klanten te informeren over hoe hun gegevens worden gebruikt en welke middelen zijn beschikbaar om deze te beschermen. Bovendien moeten bedrijven zich aan de wetten houden die relevante privacybeveiligingsmaatregelen regelen, zoals GDPR (General Data Protection Regulation) in Europa. Privacy is essentieel voor het bouwen van betrouw en vertrouwen tussen bedrijven en hun klanten, waardoor bedrijven kunnen concurreren in een markt met strengere eisen. In het algemeen kan men zeggen dat privacy een cruciaal aspect is bij het ontwikkelen van succesvolle bedrijfsstrategies.


### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
It's a Dutch speaking drop in replacement for `meta-llama/Llama-2-7b-chat-hf` and the non-waitlist mirror `daryl149/llama-2-7b-chat-hf`.

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

It's a Dutch speaking drop in replacement for `meta-llama/Llama-2-7b-chat-hf` and the non-waitlist mirror `daryl149/llama-2-7b-chat-hf`.

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
Do use it for further finetuning and let us know!

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
Don't be evil.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->
- It's not quite perfect Dutch yet, but a very promising start.

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->


## How to Get Started with the Model

If you already have a pipeline running llama 2 7B chat in huggingface format, just call this one instead. 
**N.B.** Set pad_token_id=18610 in your generator, otherwise it returns gibberish.

## Training Details

### Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure 

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
We reached 32 tokens/second on a V100S without trying anything fancy.

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Data Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Yes.

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

V100S big boi instances, kindly sponsored by OVHCloud


#### Software

[More Information Needed]

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Model Card Contact

[More Information Needed]