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 Chat by LeoLM

 »  All LLMs  »  LeoLM  »  Leo Hessianai 7B Chat   URL Share it on

  4228   
  Autotrain compatible   Conversational   Custom code Dataset:freedomintelligence/al... Dataset:freedomintelligence/ev...   Dataset:leolm/german poems   Dataset:leolm/german songs   Dataset:leolm/openschnabeltier   Dataset:openassistant/oasst-de   De   En   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/LeoLM/leo-hessianai-7b-chat 

Leo Hessianai 7B Chat Benchmarks

ARC: 52.56 vs 96.7 (so35)-45.6%
HellaSwag: 77.61 vs 95.3 (gpt4)-18.6%
MMLU: 45.58 vs 88.3 (so35)-48.4%
TruthfulQA: 44.89 vs 59 (gpt4)-23.9%
WinoGrande: 69.93 vs 87.5 (gpt4)-20.1%
GSM8K: 5.16 vs 96.4 (so35)-94.6%
LLME Score: 0.20232
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 Chat (LeoLM/leo-hessianai-7b-chat)

Leo Hessianai 7B Chat Parameters and Internals

Model Type 
Causal decoder-only transformer language model, Text generation
Use Cases 
Areas:
German open-source and commercial LLM research
Applications:
Text generation, Writing, Explanation and discussion
Primary Use Cases:
German chat applications
Limitations:
Math, Advanced reasoning
Considerations:
Developers should perform safety testing and tuning tailored to their specific applications.
Additional Notes 
Built on Llama-2, LeoLM aims to accelerate German open-source and commercial LLM research.
Supported Languages 
English (High), German (High)
Training Details 
Data Sources:
LeoLM/OpenSchnabeltier, OpenAssistant/OASST-DE, FreedomIntelligence/alpaca-gpt4-deutsch, FreedomIntelligence/evol-instruct-deutsch, LeoLM/German_Poems, LeoLM/German_Songs
Data Volume:
67530728 tokens
Methodology:
Finetuned on a selection of German instruction datasets
Context Length:
8000
Hardware Used:
HessianAI supercomputer 42
Model Architecture:
Transformer
Input Output 
Input Format:
ChatML format
Accepted Modalities:
Text
Output Format:
Text
Performance Tips:
Use flash-attention2 for faster inference.
LLM NameLeo Hessianai 7B Chat
Repository 🤗https://huggingface.co/LeoLM/leo-hessianai-7b-chat 
Model Size7b
Required VRAM13.5 GB
Updated2024-12-22
MaintainerLeoLM
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen de
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizer
Padding Token<PAD>
Vocabulary Size32128
Torch Data Typefloat16

Quantized Models of the Leo Hessianai 7B Chat

Model
Likes
Downloads
VRAM
Leo Hessianai 7B Chat GGUF42012 GB
Leo Hessianai 7B Chat GPTQ0573 GB
Leo Hessianai 7B Chat AWQ1213 GB

Best Alternatives to Leo Hessianai 7B Chat

Best Alternatives
Context / RAM
Downloads
Likes
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB29350
SuperNeuralDreadDevil 8B128K / 16.1 GB1551
Falcon3 7B Instruct32K / 14.8 GB411428
Falcon3 7B Instruct 1.58bit32K / 3.3 GB44113
FalconSlerp2 7B32K / 14.9 GB60
Llama 2 7B 32K Instruct32K / 13.5 GB6101159
Qwen2 7B Instruct Llama32K / 15.2 GB113
Qwen2 7B Instruct Mistral32K / 15.2 GB141
AIRIC The Mistral32K / 14.4 GB7507
...ls Vikhr 7B Instruct 0.4 4bits32K / 5.2 GB100
Note: green Score (e.g. "73.2") means that the model is better than LeoLM/leo-hessianai-7b-chat.

Rank the Leo Hessianai 7B Chat 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? 40066 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 v20241217
  Support LLM Explorer