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

Cypher Mini 1.8B by aloobun

 »  All LLMs  »  aloobun  »  Cypher Mini 1.8B   URL Share it on

  111   

Cypher Mini 1.8B is an open-source language model by aloobun. Features: 1.8b LLM, VRAM: 3.7GB, Context: 16K, License: apache-2.0, HF Score: 43.1, LLM Explorer Score: 0.16, Arc: 39.6, HellaSwag: 67.5, MMLU: 31.1, TruthfulQA: 40.4, WinoGrande: 65.2, GSM8K: 14.5.

  Conversational   Custom code Dataset:locutusque/hercules-v3...   Endpoints compatible   Finetuned   Gpt4   H2oai   Mistral   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/aloobun/Cypher-Mini-1.8B 

Cypher Mini 1.8B Benchmarks

ARC: 39.59 vs 96.7 (so35)-59.1%
HellaSwag: 67.45 vs 95.3 (gpt4)-29.2%
MMLU: 31.14 vs 88.3 (so35)-64.7%
TruthfulQA: 40.44 vs 59 (gpt4)-31.5%
WinoGrande: 65.19 vs 87.5 (gpt4)-25.5%
GSM8K: 14.48 vs 96.4 (so35)-85%
LLME Score: 0.15875
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cypher Mini 1.8B (aloobun/Cypher-Mini-1.8B)
🌟 Advertise your project 🚀

Cypher Mini 1.8B Parameters and Internals

Model Type 
text generation
Additional Notes 
This is an experimental model finetuned on a combination of Hercules v3 dataset and a private dataset.
Training Details 
Data Sources:
Locutusque/Hercules-v3.0, Private dataset
Methodology:
Mixture of experts approach
Input Output 
Input Format:
<|system|>~~<|prompt|>~~<|answer|>
Accepted Modalities:
text
Performance Tips:
Hyperparameters include adamw optimizer with eps of 1e-8, cosine decay with 20% warmup, and learning rate of 2e-5.
LLM NameCypher Mini 1.8B
Repository 🤗https://huggingface.co/aloobun/Cypher-Mini-1.8B 
Model Size1.8b
Required VRAM3.7 GB
Updated2026-04-04
Maintaineraloobun
Model Typemistral
Model Files  3.0 GB: 1-of-2   0.7 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.37.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Cypher Mini 1.8B

Best Alternatives
Context / RAM
Downloads
Likes
H2o Danube 1.8B Chat16K / 3.7 GB14955
H2o Danube 1.8B Base16K / 3.7 GB16243
H2o Danube 1.8B Sft16K / 3.7 GB10711
PixieZehirNano16K / 3.7 GB100
Cypher CoT 1.8B16K / 3.7 GB121
...1.8B Chat Sft Merge Fourier V116K / 7.3 GB51
H2o Danube2 1.8B Chat8K / 3.7 GB38762
H2o Danube2 1.8B Base8K / 3.7 GB40447
H2o Danube2 1.8B Sft8K / 3.7 GB1206
Binary Clumsy Bear8K / 7.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than aloobun/Cypher-Mini-1.8B.

Rank the Cypher Mini 1.8B 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? 52721 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