---
language:
- nl
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
- llama
- lora
- adapters
datasets:
- BramVanroy/dutch_chat_datasets
base_model: BramVanroy/Llama-2-13b-chat-dutch
inference: false
model_creator: Bram Vanroy
model_type: llama
prompt_template: '[INST] <>
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.
<>
{prompt}[/INST]
'
quantized_by: TheBloke
model-index:
- name: Llama-2-13b-chat-dutch
results: []
---
# Llama 2 13B Chat Dutch - AWQ
- Model creator: [Bram Vanroy](https://huggingface.co/BramVanroy)
- Original model: [Llama 2 13B Chat Dutch](https://huggingface.co/BramVanroy/Llama-2-13b-chat-dutch)
## Description
This repo contains AWQ model files for [Bram Vanroy's Llama 2 13B Chat Dutch](https://huggingface.co/BramVanroy/Llama-2-13b-chat-dutch).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.
It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-GGUF)
* [Bram Vanroy's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/BramVanroy/Llama-2-13b-chat-dutch)
## Prompt template: Llama-2-Chat
```
[INST] <>
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.
<>
{prompt}[/INST]
```
## Licensing
The creator of the source model has listed its license as `cc-by-nc-sa-4.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Bram Vanroy's Llama 2 13B Chat Dutch](https://huggingface.co/BramVanroy/Llama-2-13b-chat-dutch).
## Provided files and AWQ parameters
For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-AWQ/tree/main) | 4 | 128 | [Dolly 15K Dutch](https://huggingface.co/datasets/BramVanroy/dolly-15k-dutch) | 4096 | 7.25 GB
## Serving this model from vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
```shell
python3 python -m vllm.entrypoints.api_server --model TheBloke/Llama-2-13B-Chat-Dutch-AWQ --quantization awq
```
When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/Llama-2-13B-Chat-Dutch-AWQ", quantization="awq")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
## How to use this AWQ model from Python code
### Install the necessary packages
Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.0.2 or later
```shell
pip3 install autoawq
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### You can then try the following example code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_name_or_path = "TheBloke/Llama-2-13B-Chat-Dutch-AWQ"
# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
prompt = "Tell me about AI"
prompt_template=f'''[INST] <>
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.
<>
{prompt}[/INST]
'''
print("\n\n*** Generate:")
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
tokens,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
max_new_tokens=512
)
print("Output: ", tokenizer.decode(generation_output[0]))
# Inference can also be done using transformers' pipeline
from transformers import pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Compatibility
The files provided are tested to work with [AutoAWQ](https://github.com/casper-hansen/AutoAWQ), and [vLLM](https://github.com/vllm-project/vllm).
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is not yet compatible with AWQ, but a PR is open which should bring support soon: [TGI PR #781](https://github.com/huggingface/text-generation-inference/issues/781).
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
# Original model card: Bram Vanroy's Llama 2 13B Chat Dutch
# Llama-2-13b-chat-dutch
This model is a fine-tuned version of [BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny](https://huggingface.co/BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny)
on the [BramVanroy/dutch_chat_datasets](https://huggingface.co/datasets/BramVanroy/dutch_chat_datasets) dataset on a context of 4096 tokens.
See the original [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) for more information, intended use, and biases.
If you use this model or refer to it, please use the following citation:
Bram Vanroy. (2023). Llama v2 13b: Finetuned on Dutch Conversational Data. Hugging Face. https://doi.org/10.57967/HF/1018
```bibtex
@misc{https://doi.org/10.57967/hf/1018,
doi = {10.57967/HF/1018},
url = {https://huggingface.co/BramVanroy/Llama-2-13b-chat-dutch},
author = {{Bram Vanroy}},
title = {{Llama} v2 13b: {Finetuned} on {Dutch} Conversational Data},
publisher = {{Hugging} {Face}},
year = {2023}
}
```
## Model description
I could not get the original Llama 2 13B to produce much Dutch, even though the description paper indicates that it was trained on a (small) portion of Dutch data. I therefore
continued training the original Llama 2 13B checkpoint on Dutch data [in regular CLM](https://huggingface.co/BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny). In a second
step I finetuned that model on a collection of synthetic (translated) instruction and chat datasets that I have [collected](https://huggingface.co/datasets/BramVanroy/dutch_chat_datasets).
See their pages for licensing, usage, creation, and citation information.
- https://huggingface.co/datasets/BramVanroy/dolly-15k-dutch
- https://huggingface.co/datasets/BramVanroy/alpaca-cleaned-dutch-baize
- https://huggingface.co/datasets/BramVanroy/stackoverflow-chat-dutch
- https://huggingface.co/datasets/BramVanroy/quora-chat-dutch
This model is the result of that process. While not perfect by any means, it can perform reasonably well in Dutch depending on the prompts. It is also decent at helping with programming tasks.
## Intended uses & limitations
Depending on the prompt, the model can return good results considering that it is only 13B in size and was only marginally pretrained on Dutch. That being said, the
model was not trained on human feedback and contains no safe-guards so it may produce unexpected and even offensive content depending on the query. The only attempt
of a safe-guard is the default prompt that it was trained on, which was
> Je bent een behulpzame, respectvolle en eerlijke assistent. Antwoord altijd zo behulpzaam mogelijk. Je antwoorden mogen geen schadelijke, onethische, racistische, seksistische, gevaarlijke of illegale inhoud bevatten. Zorg ervoor dat je antwoorden sociaal onbevooroordeeld en positief van aard zijn.\n\nAls een vraag nergens op slaat of feitelijk niet coherent is, leg dan uit waarom in plaats van iets niet correct te antwoorden. Als je het antwoord op een vraag niet weet, deel dan geen onjuiste informatie.\
Use with caution and at your own risk!
Because the model was trained on synthetic data, translated with OpenAI's API, you cannot use this model to create a competitive product to theirs.
## Training procedure
Trained with 4096 tokens context length. The dataset was preprocessed so that as many as possible dialogs were put in a single batch, without disrupting
dialogs. In other words, a dialog was never split up over different sequences or batches. During training, the human prompts were ignored in back propagation.
Trained with LoRA targetting ["q_proj", "v_proj"] in 4 bit and merged before upload. Trained with Flash Attention as borrowed from [here](https://github.com/philschmid/deep-learning-pytorch-huggingface/blob/main/training/utils/llama_patch.py).
The adapters are in the `adapters` branch.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0193 | 0.09 | 20 | 1.1583 |
| 0.9743 | 0.17 | 40 | 1.1339 |
| 0.9159 | 0.26 | 60 | 1.1218 |
| 0.9131 | 0.35 | 80 | 1.1153 |
| 0.8816 | 0.44 | 100 | 1.1130 |
| 0.8977 | 0.52 | 120 | 1.1069 |
| 0.9061 | 0.61 | 140 | 1.1025 |
| 0.8672 | 0.7 | 160 | 1.1024 |
| 0.8956 | 0.79 | 180 | 1.0971 |
| 0.8514 | 0.87 | 200 | 1.0995 |
| 0.8357 | 0.96 | 220 | 1.0952 |
| 0.8294 | 1.05 | 240 | 1.0964 |
| 0.8531 | 1.13 | 260 | 1.0947 |
| 0.8321 | 1.22 | 280 | 1.0951 |
| 0.8365 | 1.31 | 300 | 1.0910 |
| 0.8616 | 1.4 | 320 | 1.0894 |
| 0.8397 | 1.48 | 340 | 1.0904 |
| 0.861 | 1.57 | 360 | 1.0880 |
| 0.8116 | 1.66 | 380 | 1.0871 |
| 0.8285 | 1.74 | 400 | 1.0855 |
| 0.8603 | 1.83 | 420 | 1.0856 |
| 0.8126 | 1.92 | 440 | 1.0848 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3