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

13B HyperMantis by digitous

 »  All LLMs  »  digitous  »  13B HyperMantis   URL Share it on

  1726   
  Alpaca   Autotrain compatible   Chat   En   Endpoints compatible   Instruct   Llama   Merge   Mix   Model merge   Pytorch   Region:us   Roleplay   Sharded   Vicuna
Model Card on HF 🤗: https://huggingface.co/digitous/13B-HyperMantis 

13B HyperMantis Benchmarks

ARC: 58.53 vs 96.7 (so35)-39.5%
HellaSwag: 82.2 vs 95.3 (gpt4)-13.7%
MMLU: 50.61 vs 88.3 (so35)-42.7%
TruthfulQA: 47.5 vs 59 (gpt4)-19.5%
WinoGrande: 76.24 vs 87.5 (gpt4)-12.9%
GSM8K: 10.39 vs 96.4 (so35)-89.2%
LLME Score: 0.12704
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
13B HyperMantis (digitous/13B-HyperMantis)
🌟 Advertise your project 🚀

13B HyperMantis Parameters and Internals

Model Type 
chat, instruct, roleplay
Use Cases 
Areas:
roleplay, text-based adventures, chatbot, instruction following
Applications:
Roleplay Adventure, Chat Interface, TavernAI character
Primary Use Cases:
Roleplay Adventure
Considerations:
Adjust settings to suit specific roleplay or chat interactions
Additional Notes 
Model seems to respond best to Alpaca's formality format, less effective with Human/Assistant format.
Supported Languages 
en (full)
Input Output 
Input Format:
Alpaca instruct format
Accepted Modalities:
text
Output Format:
text-based responses with detailed storytelling
Performance Tips:
Use specific settings in KoboldAI for optimal performance
LLM Name13B HyperMantis
Repository 🤗https://huggingface.co/digitous/13B-HyperMantis 
Model Size13b
Required VRAM26.1 GB
Updated2025-09-18
Maintainerdigitous
Model Typellama
Instruction-BasedYes
Model Files  10.5 GB: 1-of-3   10.4 GB: 2-of-3   5.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the 13B HyperMantis

Model
Likes
Downloads
VRAM
13B HyperMantis GGUF31425 GB
13B HyperMantis AWQ147 GB

Best Alternatives to 13B HyperMantis

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB1101469
CodeLlama 13B Instruct Hf16K / 26 GB17336154
CodeLlama 13B MORepair16K / 26 GB32
CodeLlama 13B Instruct Hf16K / 26 GB101825
TableLLM 13B16K / 26 GB131629
NexusRaven 13B16K / 26 GB12104
Panda Coder 13B16K / 26 GB713
... Llama 2 13B Instruct Text2sql16K / 26 GB2327
Gen Sim16K / 0.3 GB52
Llama 3 13B Instruct Ft8K / 26.1 GB52
Note: green Score (e.g. "73.2") means that the model is better than digitous/13B-HyperMantis.

Rank the 13B HyperMantis 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? 51435 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