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

Defne Llama3.1 8B by Eurdem

 »  All LLMs  »  Eurdem  »  Defne Llama3.1 8B   URL Share it on

  3829   
  Autotrain compatible   Conversational   De   En   Endpoints compatible   Es   Fr   Instruct   It   Llama   Llama-3   Region:us   Safetensors   Sharded   Tensorflow   Tr
Model Card on HF 🤗: https://huggingface.co/Eurdem/Defne-llama3.1-8B 

Defne Llama3.1 8B Benchmarks

MMLU Pro: 31.84
GPQA: 6.15
MUSR: 13.54
BBH: 32.82
IFEval: 50.36 vs 88 (so35)-42.8%
MATH Lvl 5: 16.01
LLME Score: 0.29822
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Defne Llama3.1 8B (Eurdem/Defne-llama3.1-8B)

Defne Llama3.1 8B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, entertainment
Applications:
chatbots
Primary Use Cases:
friendly informational chat assistance
Limitations:
Possible bias in outputs depending on the dataset used
Supported Languages 
en (fluent), tr (fluent), de (partial), fr (partial), it (partial), es (partial)
Training Details 
Data Sources:
Turkish dataset (~4 mio tokens)
Data Volume:
~4 mio tokens
Methodology:
Fine-tuning, Merging with VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
Input Output 
Input Format:
system and user role-based chat messages
Accepted Modalities:
text
Output Format:
textual chat responses
Performance Tips:
Use appropriate sampling techniques to adjust creativity.
LLM NameDefne Llama3.1 8B
Repository 🤗https://huggingface.co/Eurdem/Defne-llama3.1-8B 
Model Size8b
Required VRAM16.1 GB
Updated2025-05-15
MaintainerEurdem
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 Languagesen tr de fr it es
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Defne Llama3.1 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB5687104
UltraLong Thinking4192K / 16.1 GB2712
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB102715
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB499441
Zero Llama 3.1 8B Beta61048K / 16.1 GB1051
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB532
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB392
Note: green Score (e.g. "73.2") means that the model is better than Eurdem/Defne-llama3.1-8B.

Rank the Defne Llama3.1 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? 47368 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