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

Leo Hessianai 7B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Leo Hessianai 7B AWQ   URL Share it on

  26   
  4-bit   Autotrain compatible   Awq Base model:leolm/leo-hessianai... Base model:quantized:leolm/leo...   Custom code Dataset:bjoernp/tagesschau-201... Dataset:oscar-corpus/oscar-230...   Dataset:wikipedia   De   En   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/leo-hessianai-7B-AWQ 

Leo Hessianai 7B AWQ Benchmarks

LLME Score: 0.1216
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Leo Hessianai 7B AWQ (TheBloke/leo-hessianai-7B-AWQ)

Leo Hessianai 7B AWQ Parameters and Internals

Model Type 
causal, transformer, text generation
Use Cases 
Areas:
German open-source and commercial LLM research
Additional Notes 
LeoLM extends Llama-2's capabilities into German through continued pretraining.
Supported Languages 
en (English), de (German)
Training Details 
Data Sources:
oscar-corpus/OSCAR-2301, wikipedia, bjoernp/tagesschau-2018-2023
Methodology:
Continued pretraining on German-language and mostly locality specific text.
Context Length:
8000
Hardware Used:
HessianAI's new supercomputer
Model Architecture:
Causal decoder-only transformer language model
LLM NameLeo Hessianai 7B AWQ
Repository 🤗https://huggingface.co/TheBloke/leo-hessianai-7B-AWQ 
Model NameLeo Hessianai 7B
Model CreatorLAION LeoLM
Base Model(s)  Leo Hessianai 7B   LeoLM/leo-hessianai-7b
Model Size7b
Required VRAM3.9 GB
Updated2025-06-02
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagesen de
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length8192
Model Max Length8192
Transformers Version4.32.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Leo Hessianai 7B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB121
Yarn Llama 2 7B 64K AWQ64K / 3.9 GB170
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB60732
Calm2 7B Chat AWQ32K / 4.4 GB1221
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB90
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB11260
CodeLlama 7B Instruct AWQ16K / 3.9 GB3944
Pandalyst 7B V1.2 AWQ16K / 3.9 GB111
Tora Code 7B V1.0 AWQ16K / 3.9 GB100
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB101
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/leo-hessianai-7B-AWQ.

Rank the Leo Hessianai 7B AWQ 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? 47796 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