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

Fireball 12B V1.13a Philosophers by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  Fireball 12B V1.13a Philosophers   URL Share it on

  10   

Fireball 12B V1.13a Philosophers is an open-source language model by EpistemeAI. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, LLM Explorer Score: 0.19.

Base model:epistemeai/fireball... Base model:finetune:epistemeai...   En   Endpoints compatible   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Fireball-12B-v1.13a-philosophers 

Fireball 12B V1.13a Philosophers Benchmarks

MMLU Pro: 26.3
GPQA: 6.82
MUSR: 9.98
BBH: 30.34
IFEval: 8.76 vs 88 (so35)-90%
MATH Lvl 5: 4.61
LLME Score: 0.19123
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fireball 12B V1.13a Philosophers (EpistemeAI/Fireball-12B-v1.13a-philosophers)
🌟 Advertise your project 🚀

Fireball 12B V1.13a Philosophers Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
philosophy of science, mathematics, epistemology
Primary Use Cases:
simulated consciousness, emotions
Additional Notes 
Pretrained base model without moderation mechanisms. Requires guardrailing using SentinelShield AI.
Supported Languages 
en (high proficiency)
Training Details 
Methodology:
Super fine-tune with philosophy of science, math, epistemology dataset.
Context Length:
128000
Model Architecture:
Transformer with 40 layers, 5,120 dimension, 14,436 hidden dimension, SwiGLU activation function, 32 heads, 8 kv-heads (GQA), 128k vocabulary size with rotary embeddings (theta = 1M).
Input Output 
Input Format:
Alpaca style prompt
Accepted Modalities:
text
Output Format:
generated text in response to input instructions
Performance Tips:
Use a temperature of 0.3 for generating text.
LLM NameFireball 12B V1.13a Philosophers
Repository 🤗https://huggingface.co/EpistemeAI/Fireball-12B-v1.13a-philosophers 
Base Model(s)  EpistemeAI/Fireball-Mistral-Nemo-12B-cot-orcas   EpistemeAI/Fireball-Mistral-Nemo-12B-cot-orcas
Model Size12b
Required VRAM24.5 GB
Updated2026-04-10
MaintainerEpistemeAI
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5   4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typefloat16

Best Alternatives to Fireball 12B V1.13a Philosophers

Best Alternatives
Context / RAM
Downloads
Likes
Celestial Queen 12B1000K / 24.5 GB3379
Celestial Queen 12B Heretic1000K / 24.5 GB333
...s PersonalityEngine V1.1.0 12B1000K / 24.5 GB65145
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB2220
MN 12B Mag Mell R11000K / 24.5 GB1458236
...n Eris BMO Violent GRPO V0.4201000K / 24.5 GB923
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB1374138
Impish Nemo 12B1000K / 24.5 GB207870
DoublePotato Mistral Nemo 13B1000K / 26.8 GB121
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Fireball-12B-v1.13a-philosophers.

Rank the Fireball 12B V1.13a Philosophers 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? 53127 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