---
base_model: LeoLM/leo-hessianai-7b
license: cc-by-4.0
datasets:
- caretech-owl/wikiquote-de-quotes
language:
- de
library_name: adapter-transformers
pipeline_tag: text-generation
---

# Model Card for Model ID

This model is trained to generate german quotes for a given author. 
The full model can be tested at [spaces/caretech-owl/quote-generator-de](https://huggingface.co/spaces/caretech-owl/quote-generator-de),
here we provide the LORA adapter files for loading on top of the base model [LeoLM/leo-hessianai-7b](https://huggingface.co/LeoLM/leo-hessianai-7b).



## Model Details

### Model Description

This fine-tuned model has been trained on the [caretech-owl/wikiquote-de-quotes](https://huggingface.co/datasets/caretech-owl/wikiquote-de-quotes) dataset. 
The model was trained on a prompt like this
```python

prompt_format = "<|im_start|>system\
Dies ist eine Unterhaltung zwischen einem\
intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt Antworten in Form von Zitaten.<|im_end|>\n\
<|im_start|>user\
Zitiere {author}<|im_end|>\n<\
|im_start|>assistant\n{quote}<|im_end|>\n"
```
Where author is itended to be provided by the user, the quote is of format ```quote + " - " + author```.
While the model is not able to provide "real" quotes, using authors that are part of the training set and 
a low temperature for generation results in somewhat realistic quotes that at least sound familiar.


- **Developed by:** [CareTech OWL](https://www.caretech-owl.de/)
- **Model type:** LLAMA2 LORA adapter
- **Language(s) (NLP):** German
- **License:** [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/)
- **Finetuned from model:** [LeoLM/leo-hessianai-7b](https://huggingface.co/LeoLM/leo-hessianai-7b)

## Uses

```python
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    pipeline
)
base_model = AutoModelForCausalLM.from_pretrained('LeoLM/leo-hessianai-7b')
tokenizer = AutoTokenizer.from_pretrained('LeoLM/leo-hessianai-7b', 
                                          trust_remote_code=False)
tokenizer.pad_token = tokenizer.eos_token

base_model.load_adapter('caretech-owl/leo-hessianai-7B-ggpq-german-quotes-lora', adapter_name='leo-hessianai-7B-ggpq-german-quotes-lora')
base_model.enable_adapters()



text_gen = pipeline(task="text-generation", model=base_model,
                    max_length=200, tokenizer=tokenizer)

system_prompt = """Dies ist eine Unterhaltung zwischen \
einem intelligenten, hilfsbereitem \
KI-Assistenten und einem Nutzer.
Der Assistent gibt Antworten in Form von Zitaten."""
prompt_format = "<|im_start|>system\n{system_prompt}\
<|im_end|>\n<|im_start|>user\nZitiere {prompt}\
<|im_end|>\n<|im_start|>assistant\n"

def get_quote(author:str, max_length:int=200):
    query = prompt_format.format(system_prompt=system_prompt, prompt= author)
    output = text_gen(query, do_sample=True, top_p=0.95, max_length=max_length, 
                      return_full_text=False, pad_token_id=tokenizer.pad_token_id)
    print(output[0]['generated_text'])


get_quote("Heinrich Heine")
```



## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: gptq
- bits: 8
- tokenizer: None
- dataset: None
- group_size: 32
- damp_percent: 0.1
- desc_act: True
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: None
- block_name_to_quantize: None
- module_name_preceding_first_block: None
- batch_size: 1
- pad_token_id: None
- use_exllama: True
- max_input_length: None
- exllama_config: {'version': <ExllamaVersion.ONE: 1>}
- cache_block_outputs: True

### Framework versions


- PEFT 0.6.2