Llama 2 7B German Assistant V3 by flozi00

 ยป  All LLMs  ยป  flozi00  ยป  Llama 2 7B German Assistant V3   URL Share it on

  Autotrain compatible   Dataset:flozi00/conversations   De   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Llama 2 7B German Assistant V3 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B German Assistant V3 (flozi00/Llama-2-7b-german-assistant-v3)
๐ŸŒŸ Advertise your project ๐Ÿš€

Llama 2 7B German Assistant V3 Parameters and Internals

Model Type 
Conversational, Instruction Following
Additional Notes 
The dataset used is cleaned and deduplicated, with no codes inside.
Supported Languages 
German (Native)
Training Details 
Data Sources:
flozi00/conversations
Methodology:
Finetuning for German instructions and conversations
Hardware Used:
100% renewable energy powered hardware
Model Architecture:
Llama version 2
LLM NameLlama 2 7B German Assistant V3
Repository ๐Ÿค—https://huggingface.co/flozi00/Llama-2-7b-german-assistant-v3 
Model Size7b
Required VRAM13.5 GB
Updated2025-09-23
Maintainerflozi00
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesde
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 7B German Assistant V3

Best Alternatives
Context / RAM
Downloads
Likes
A6 L1024K / 16.1 GB2010
A3.41024K / 16.1 GB130
A5.41024K / 16.1 GB120
A2.41024K / 16.1 GB120
M1024K / 16.1 GB1270
1571024K / 16.1 GB1010
1241024K / 16.1 GB930
1621024K / 16.1 GB600
2 Very Sci Fi1024K / 16.1 GB3170
1181024K / 16.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than flozi00/Llama-2-7b-german-assistant-v3.

Rank the Llama 2 7B German Assistant V3 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51544 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124