LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama3 German 8B by DiscoResearch

 »  All LLMs  »  DiscoResearch  »  Llama3 German 8B   URL Share it on

  454   
  Arxiv:2404.10830   Autotrain compatible   De   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DiscoResearch/Llama3-German-8B 

Llama3 German 8B Benchmarks

LLME Score: 0.21018
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 German 8B (DiscoResearch/Llama3-German-8B)

Llama3 German 8B Parameters and Internals

Model Type 
Text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
German text generation and understanding
Primary Use Cases:
Language modeling in German
Limitations:
Base model should be fine-tuned before use
Additional Notes 
The model was jointly developed by DiscoResearch and Occiglot with support from DFKI and hessian.Ai. Document packing strategy improved training efficiency.
Supported Languages 
German (High Proficiency)
Training Details 
Data Sources:
occiglot-fineweb-0.5, LLM-Datasets, Common-Crawl
Data Volume:
65B German tokens
Methodology:
Continuous pretraining with document packing strategy.
Context Length:
8192
Training Time:
~60 hours
Hardware Used:
128 GPUs on hessian.Ai 42
Model Architecture:
Based on Meta's Llama3-8B
Input Output 
Input Format:
Prompts should be structured for language generation tasks.
Accepted Modalities:
text
Output Format:
Textual output
Release Notes 
Version:
v0.1
Notes:
Llama3-German-8B-v0.1 is released for German language tasks.
LLM NameLlama3 German 8B
Repository 🤗https://huggingface.co/DiscoResearch/Llama3-German-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-02-05
MaintainerDiscoResearch
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesde
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3 German 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB6623678
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
Mpasila Viking 8B1024K / 16.1 GB590
41024K / 16.1 GB3220
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
161024K / 16.1 GB1690
Because Im Bored Nsfw11024K / 16.1 GB661
111024K / 16.1 GB1130
NBeerbower Narrative 8B 64K1024K / 16.1 GB321
Note: green Score (e.g. "73.2") means that the model is better than DiscoResearch/Llama3-German-8B.

Rank the Llama3 German 8B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer