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

L3.1 Purosani 2 8B by djuna

 »  All LLMs  »  djuna  »  L3.1 Purosani 2 8B   URL Share it on

  66   
  Merged Model   Autotrain compatible Base model:arcee-ai/llama-3.1-... Base model:blackroot/llama-3-8...   Base model:djuna/l3.1-forsths Base model:djuna/l3.1-suze-vum... Base model:grimjim/llama-3-ins... Base model:hf-100/llama-3-spel... Base model:resplendentai/smart... Base model:thudm/longwriter-ll... Base model:unsloth/meta-llama-...   Conversational   Endpoints compatible   Instruct   Llama   Lora   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/djuna/L3.1-Purosani-2-8B 

L3.1 Purosani 2 8B Benchmarks

MMLU Pro: 30.57
GPQA: 6.82
MUSR: 8.3
BBH: 31.39
IFEval: 49.88 vs 88 (so35)-43.3%
MATH Lvl 5: 11.71
LLME Score: 0.26706
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

L3.1 Purosani 2 8B Parameters and Internals

Model Type 
transformers
Additional Notes 
This is a merge of pre-trained language models created using the della_linear merge method with int8_mask, epsilon: 0.1 and lambda: 1.0 parameters.
LLM NameL3.1 Purosani 2 8B
Repository 🤗https://huggingface.co/djuna/L3.1-Purosani-2-8B 
Base Model(s)  hf-100/Llama-3-Spellbound-Instruct-8B-0.3   unsloth/Meta-Llama-3.1-8B   arcee-ai/Llama-3.1-SuperNova-Lite   ... Instruct Abliteration LoRA 8B   THUDM/LongWriter-llama3.1-8b   Smarts Llama3   djuna/L3.1-Suze-Vume-2-calc   djuna/L3.1-ForStHS   Llama 3 8B Abomination LORA   hf-100/Llama-3-Spellbound-Instruct-8B-0.3   unsloth/Meta-Llama-3.1-8B   arcee-ai/Llama-3.1-SuperNova-Lite   grimjim/Llama-3-Instruct-abliteration-LoRA-8B   THUDM/LongWriter-llama3.1-8b   ResplendentAI/Smarts_Llama3   djuna/L3.1-Suze-Vume-2-calc   djuna/L3.1-ForStHS   Blackroot/Llama-3-8B-Abomination-LORA
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2025-06-11
Maintainerdjuna
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
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
LoRA ModelYes
Torch Data Typebfloat16
L3.1 Purosani 2 8B (djuna/L3.1-Purosani-2-8B)

Best Alternatives to L3.1 Purosani 2 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3395108
UltraLong Thinking4192K / 16.1 GB5072
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB92315
Zero Llama 3.1 8B Beta61048K / 16.1 GB10941
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB207045
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB932
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB233
Note: green Score (e.g. "73.2") means that the model is better than djuna/L3.1-Purosani-2-8B.

Rank the L3.1 Purosani 2 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? 48075 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 v20241124
  Support LLM Explorer