Downloads · 30 days
29
27% of all-time downloads
dominik-reiner/wolfgang-lm-75M-base-v1
wolfgang-lm-75M-base-v1 is a text generation model from dominik-reiner. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Wolfgang-LM is a historical language model trained to replicate the linguistic style of late 18th and early 19th-century German literature. This is the base pretrained model, designed for historical text generation an…
Downloads · 30 days
29
27% of all-time downloads
All-time downloads
106
Public
Parameters
75.5M
302 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors302 MB · 99%
From the Hugging Face model README
Wolfgang-LM is a historical language model trained to replicate the linguistic style of late 18th and early 19th-century German literature. This is the base pretrained model, designed for historical text generation and as a foundation for style-specific fine-tuning.
⚠️ Research Preview: This model is a research artifact for exploring historical linguistics and style transfer. It should not be used as a source of factual information.
dominik-reiner/wolfgang-lm-75M-instruct-v1 for this).The model was trained on a strictly curated corpus to ensure historical authenticity, sourced from the Deutsches Textarchiv (DTA).
This model can be used with the transformers library.
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "dominik-reiner/wolfgang-lm-75M-base-v1"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Die Natur ist"
inputs = tokenizer(prompt, return_tensors="pt")
# Generate text
outputs = model.generate(
**inputs,
max_new_tokens=100,
temperature=0.5,
top_p=0.8,
top_k=15,
repetition_penalty=1.1,
do_sample=True
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))