From the model card
Fields below are copied from the tags and counters on the HuggingFace repository LSX-UniWue/LLaMmlein_1B_prerelease at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- LSX-UniWue
- Pipeline tag
- text-generation
- Library
- Transformers
- Weight formats
- safetensors
- License tag
other— read the license file in the repo before relying on it- Language tags
- German (de)
- Papers cited
- arXiv:2411.11171
- Datasets declared
- togethercomputer/RedPajama-Data-V2, LSX-UniWue/LLaMmlein-Dataset
- Downloads (HF counter at last fetch)
- 343,431
- Likes (HF counter at last fetch)
- 14
- Model card
- https://huggingface.co/LSX-UniWue/LLaMmlein_1B_prerelease
Use cases
- German-language text generation and completion
- Starting point for German NLP fine-tuning tasks
- Research baseline for small German language models
- Low-resource German language understanding tasks
Pros
- Trained from scratch on German — not a translation-based multilingual model
- 1B parameter scale is small enough for academic fine-tuning
- German-specific vocabulary tokenization improves efficiency over multilingual tokenizers
- University research provenance with publication forthcoming
Cons
- Prerelease checkpoint — may change significantly in the final release
- 1B scale limits complex reasoning and knowledge depth in German
- Not recommended for production use until final release stabilizes
- German-only; limited cross-lingual transfer
Tags
transformerssafetensorsllamatext-generationdedataset:togethercomputer/RedPajama-Data-V2dataset:LSX-UniWue/LLaMmlein-Datasetarxiv:2411.11171license:othertext-generation-inferenceendpoints_compatibleregion:us