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

Mika 7B by Epiculous

 »  All LLMs  »  Epiculous  »  Mika 7B   URL Share it on

  680   

Mika 7B is an open-source language model by Epiculous. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: agpl-3.0, Instruction-Based, LLM Explorer Score: 0.14, Arc: 63.5, HellaSwag: 85.4, MMLU: 59.9, GSM8K: 28.5.

  Conversational Dataset:chaoticneutrals/synthe... Dataset:chaoticneutrals/synthe...   Dataset:epiculous/gnosis Dataset:grimulkan/theory-of-mi...   Dataset:lemonilia/limarp   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Epiculous/Mika-7B 

Mika 7B Benchmarks

ARC: 63.48 vs 96.7 (so35)-34.4%
HellaSwag: 85.44 vs 95.3 (gpt4)-10.3%
MMLU: 59.85 vs 88.3 (so35)-32.2%
GSM8K: 28.51 vs 96.4 (so35)-70.4%
LLME Score: 0.14257
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mika 7B (Epiculous/Mika-7B)
🌟 Advertise your project 🚀

Mika 7B Parameters and Internals

Additional Notes 
Mika is named after a Claude-3 Opus chat persona.
Training Details 
Data Sources:
lemonilia/LimaRP, grimulkan/theory-of-mind, Epiculous/Gnosis, ChaoticNeutrals/Synthetic-RP, ChaoticNeutrals/Synthetic-Dark-RP
Methodology:
Trained in a similar manner to Fett-uccine with synthetic RP data created by Claude included.
Input Output 
Input Format:
ChatML Context Template, Mistral Instruct Template
Performance Tips:
YMMV (Your Mileage May Vary)
LLM NameMika 7B
Repository 🤗https://huggingface.co/Epiculous/Mika-7B 
Model Size7b
Required VRAM14.4 GB
Updated2026-06-02
MaintainerEpiculous
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseagpl-3.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mika 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB17920
SpydazWeb AI HumanAI RP512K / 14.4 GB241
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB60
...1 Summarize 64K LoRANET Merged128K / 14.4 GB60
Mistral 7B Instruct V0.232K / 14.4 GB31562273149
Mistral 7B Instruct V0.132K / 14.4 GB2906401835
Mistral 7B Instruct V0.232K / 14.4 GB9720
Mixtral AI CyberCoder32K / 14.3 GB00
Note: green Score (e.g. "73.2") means that the model is better than Epiculous/Mika-7B.

Rank the Mika 7B 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? 54493 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer