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

SHBA by Aryanne

 »  All LLMs  »  Aryanne  »  SHBA   URL Share it on

  5   
  Autotrain compatible Base model:aryanne/superheartb... Base model:koboldai/llama-3.1-... Base model:merge:aryanne/super... Base model:merge:koboldai/llam...   Conversational   Endpoints compatible   Llama   Merge   Mergekit   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Aryanne/SHBA 

SHBA Benchmarks

MMLU Pro: 32.13
GPQA: 7.38
MUSR: 11.12
BBH: 32.48
IFEval: 78.17 vs 88 (so35)-11.2%
MATH Lvl 5: 17.98
LLME Score: 0.30925
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SHBA (Aryanne/SHBA)

SHBA Parameters and Internals

LLM NameSHBA
Repository 🤗https://huggingface.co/Aryanne/SHBA 
Base Model(s)  SuperHeartBerg   KoboldAI/Llama-3.1-8B-BookAdventures   Aryanne/SuperHeartBerg   KoboldAI/Llama-3.1-8B-BookAdventures
Model Size8b
Required VRAM16.1 GB
Updated2025-05-02
MaintainerAryanne
Model Typellama
Model Files  1.1 GB: 1-of-17   1.1 GB: 2-of-17   1.0 GB: 3-of-17   1.0 GB: 4-of-17   1.0 GB: 5-of-17   0.9 GB: 6-of-17   1.0 GB: 7-of-17   1.0 GB: 8-of-17   1.0 GB: 9-of-17   0.9 GB: 10-of-17   1.0 GB: 11-of-17   1.0 GB: 12-of-17   1.0 GB: 13-of-17   0.9 GB: 14-of-17   1.0 GB: 15-of-17   1.0 GB: 16-of-17   0.2 GB: 17-of-17
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to SHBA

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB5517105
UltraLong Thinking4192K / 16.1 GB2622
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB139015
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB480041
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB392
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB26316679
F51024K / 16.1 GB1520
Note: green Score (e.g. "73.2") means that the model is better than Aryanne/SHBA.

Rank the SHBA 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? 47197 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