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

MythoMakiseMerged 13B by Heralax

 »  All LLMs  »  Heralax  »  MythoMakiseMerged 13B   URL Share it on

  437   
  Autotrain compatible   Endpoints compatible   F16   Ggml   Gguf   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Heralax/MythoMakiseMerged-13b 

MythoMakiseMerged 13B Benchmarks

LLME Score: 0.1175
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MythoMakiseMerged 13B (Heralax/MythoMakiseMerged-13b)
🌟 Advertise your project 🚀

MythoMakiseMerged 13B Parameters and Internals

Model Type 
conversational, roleplaying
Use Cases 
Primary Use Cases:
roleplaying, conversation simulation
Limitations:
Not accurate, Not good at tasks other than talking
Additional Notes 
Model was initially created to mimic a specific character but excels in general banter and roleplay.
Training Details 
Data Sources:
lines extracted from the script of Steins;Gate
Data Volume:
~1300 high-quality training examples
Methodology:
Finetune with scripted conversation grouping; integration with 33% of MythoMax-L2-13b for stability
Input Output 
Input Format:
SillyTavern prompt format
Output Format:
2 paragraphs, engaging, natural, authentic, descriptive, creative
LLM NameMythoMakiseMerged 13B
Repository 🤗https://huggingface.co/Heralax/MythoMakiseMerged-13b 
Model Size13b
Required VRAM26.7 GB
Updated2025-09-29
MaintainerHeralax
Model Typellama
Model Files  9.2 GB   26.0 GB   5.3 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   1.6 GB: 6-of-6
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Quantized Models of the MythoMakiseMerged 13B

Model
Likes
Downloads
VRAM
MythoMakiseMerged 13B GGUF74465 GB
MythoMakiseMerged 13B GPTQ377 GB
MythoMakiseMerged 13B AWQ167 GB

Best Alternatives to MythoMakiseMerged 13B

Best Alternatives
Context / RAM
Downloads
Likes
Chinese Llama 2 13B Gguf64K / 5 GB2545
... Codellama Instruct 13B Lora6416K / 26 GB240
... Instruct 13B Alpacamod Lora6416K / 26 GB190
...ama Instruct 13B Alpaca Lora6416K / 26 GB120
Openthaigpt 1.0.0 13B Chat4K / 26.2 GB11647
Estopian4K / 26 GB100
Orca 2 13B GGUF4K / 5.4 GB14367
BioinspiredLLM4K / 26 GB2726
Cat 0.54K / 26 GB4913
Nb Sau 13B 4K Step100k4K / 26 GB612
Note: green Score (e.g. "73.2") means that the model is better than Heralax/MythoMakiseMerged-13b.

Rank the MythoMakiseMerged 13B 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? 51544 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