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

Brahe by Pclanglais

 »  All LLMs  »  Pclanglais  »  Brahe   URL Share it on

  32   

Brahe is an open-source language model by Pclanglais. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: cc0-1.0, LLM Explorer Score: 0.09.

Dataset:pclanglais/brahe-novel...   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Pclanglais/Brahe 

Brahe Benchmarks

LLME Score: 0.09337
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Brahe (Pclanglais/Brahe)
🌟 Advertise your project 🚀

Brahe Parameters and Internals

Model Type 
analytical LLM, text-analysis
Use Cases 
Areas:
computational humanities
Applications:
annotation of literary texts
Primary Use Cases:
generate a list of annotations for given text
Limitations:
works best on languages included in llama-13B training
Additional Notes 
Brahe is a model inspired by characters from Daniele del Giudice's philosophical novel 'Atlante occidentale'.
Supported Languages 
English (native), French (native), German (native), Italian (native), Occitan (Gascon variety) (native)
Training Details 
Data Sources:
8,000 excerpts of literature in the public domain, synthetic and manual annotations
Data Volume:
8,000 excerpts
Methodology:
fine-tuned from llama-13B
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
annotations for literature
LLM NameBrahe
Repository 🤗https://huggingface.co/Pclanglais/Brahe 
Model Size13b
Required VRAM26 GB
Updated2026-05-14
MaintainerPclanglais
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc0-1.0
Context Length4096
Model Max Length4096
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Brahe

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB151
Yarn Llama 2 13B 128K128K / 26 GB1657113
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB110
LongAlign 13B 64K Base64K / 26 GB2843
LongAlign 13B 64K64K / 26 GB5313
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB74
Yarn Llama 2 13B 64K64K / 26 GB186518
Note: green Score (e.g. "73.2") means that the model is better than Pclanglais/Brahe.

Rank the Brahe 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? 54120 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