|
--- |
|
library_name: transformers |
|
tags: |
|
- llama2 |
|
- deutsch |
|
- german |
|
- seedbox |
|
license: llama2 |
|
datasets: |
|
- seedboxai/multitask_german_examples_32k |
|
language: |
|
- de |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
 |
|
|
|
|
|
|
|
# KafkaLM-13B-German-V0.1 |
|
|
|
**KafkaLM 13b** is a Llama2 13b model - further pre-trained on a large German dataset from Björn Plüster and LAION. [leo-hessianai-13b](https://huggingface.co/LeoLM/leo-hessianai-13b) - which was finetuned on an ensemble of popular high-quality open-source instruction sets (translated from English to German). |
|
|
|
KafkaLM 13b is a [Seedbox](https://huggingface.co/seedboxai) project trained by [Dennis Dickmann](https://huggingface.co/doubledsbv). |
|
|
|
**Why Kafka?** |
|
The models are proficient, yet creative, and have some tendencies to linguistically push boundaries 😊 |
|
|
|
|
|
## Model Details |
|
|
|
The purpose of releasing the **KafkaLM series** is to contribute to the German AI community with a set of fine-tuned LLMs that are easy to use in everyday applications across a variety of tasks. |
|
|
|
The main goal was to provide LLMs proficient in German, especially to be used in German-speaking business contexts where English alone is not sufficient. |
|
|
|
|
|
### Dataset |
|
|
|
I used a 8k filtered version of the following [seedboxai/multitask_german_examples_32k](https://huggingface.co/datasets/seedboxai/multitask_german_examples_32k) |
|
|
|
### Prompt Format |
|
|
|
|
|
This model follows the subsequent prompt format: |
|
|
|
``` |
|
<|system|> |
|
Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen.</s> |
|
<|user|> |
|
Welche Möglichkeiten der energetischen Sanierung habe ich neben Solar und Energiespeicher?</s> |
|
<|assistant|> |
|
``` |
|
|
|
### Inference |
|
|
|
Getting started with the model is straightforward |
|
|
|
```python |
|
import transformers |
|
|
|
model_id = "seedboxai/KafkaLM-13B-German-V0.1" |
|
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, trust_remote_code=True) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
|
tokenizer.padding_side = "right" |
|
tokenizer.pad_token = tokenizer.unk_token |
|
tokenizer.add_eos_token = False |
|
|
|
def generate_prompt(input): |
|
prompt = '' |
|
sys_prompt = "Du bist ein freundlicher und hilfsbereiter KI-Assistent. Du beantwortest Fragen faktenorientiert und präzise, ohne dabei relevante Fakten auszulassen." |
|
|
|
prompt += f"<|system|>\n{sys_prompt.strip()}</s>\n" |
|
prompt += f"<|user|>\n{input.strip()}</s>\n" |
|
prompt += f"<|assistant|>\n" |
|
|
|
return prompt.strip() |
|
|
|
|
|
generate_text = transformers.pipeline( |
|
model=model, tokenizer=tokenizer, |
|
return_full_text=True, |
|
task='text-generation', |
|
temperature=0.5, |
|
#max_length=8192, |
|
max_new_tokens=512, |
|
top_p=0.95, |
|
top_k=50, |
|
do_sample=True, |
|
) |
|
|
|
|
|
print(generate_text(generate_prompt("Wer ist eigentlich dieser Kafka?"))) |
|
|
|
``` |
|
|
|
## Disclaimer |
|
|
|
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. |
|
This model should only be used for research purposes. The original Llama2 license and all restrictions of datasets used to train this model apply. |
