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

Llama3 DiscoLeo Instruct 8B V0.1 by DiscoResearch

 »  All LLMs  »  DiscoResearch  »  Llama3 DiscoLeo Instruct 8B V0.1   URL Share it on

  220   
  Autotrain compatible   Conversational   De   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1 

Llama3 DiscoLeo Instruct 8B V0.1 Benchmarks

LLME Score: 0.18263
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 DiscoLeo Instruct 8B V0.1 (DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1)

Llama3 DiscoLeo Instruct 8B V0.1 Parameters and Internals

Model Type 
instruction tuning, language model
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Instruction tuning was done with the DiscoLM German dataset.
Supported Languages 
de (high proficiency)
Training Details 
Data Sources:
German Instruction dataset by DiscoResearch, high-quality German tokens from various sources
Data Volume:
65 billion German tokens
Methodology:
Full finetuning with axolotl and context-length of 8192
Context Length:
8192
Hardware Used:
hessian.Ai 42 Supercomputer
Model Architecture:
Derived from Meta's Llama3-8B model
Input Output 
Input Format:
Llama-3 chat template
Output Format:
language model outputs
LLM NameLlama3 DiscoLeo Instruct 8B V0.1
Repository 🤗https://huggingface.co/DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1 
Model Size8b
Required VRAM16.1 GB
Updated2025-05-16
MaintainerDiscoResearch
Model Typellama
Instruction-BasedYes
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
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama3 DiscoLeo Instruct 8B V0.1

Model
Likes
Downloads
VRAM
...oLeo Instruct 8B 32K V0.1 GPTQ065 GB
...oLeo Instruct 8B V0.1 4bit AWQ0125 GB

Best Alternatives to Llama3 DiscoLeo Instruct 8B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB5725104
UltraLong Thinking4192K / 16.1 GB2742
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB68215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB450641
Zero Llama 3.1 8B Beta61048K / 16.1 GB1091
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB542
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB402
Note: green Score (e.g. "73.2") means that the model is better than DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1.

Rank the Llama3 DiscoLeo Instruct 8B V0.1 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? 47399 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