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

Janus 7B by kaist-ai

 »  All LLMs  »  kaist-ai  »  Janus 7B   URL Share it on

  2187   
  Arxiv:2405.17977   Autotrain compatible   Axolotl Base model:finetune:mistral-co... Base model:mistral-community/m... Dataset:kaist-ai/multifaceted-...   En   Endpoints compatible   Generated from trainer   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kaist-ai/janus-7b 

Janus 7B Benchmarks

MMLU Pro: 20.82
GPQA: 3.02
MUSR: 14.28
BBH: 25.75
IFEval: 37.75 vs 88 (so35)-57.1%
MATH Lvl 5: 4.08
LLME Score: 0.25389
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Janus 7B (kaist-ai/janus-7b)

Janus 7B Parameters and Internals

Model Type 
Language model
Additional Notes 
Janus is adept at producing personalized responses that cater to various human preferences.
Supported Languages 
en (English)
Training Details 
Data Sources:
kaist-ai/Multifaceted-Collection-SFT
Methodology:
Supervised fine-tuning using all 196k entries of the training data from the Multifaceted-Collection.
Hardware Used:
4 GPUs
Model Architecture:
Derived from Alpindale Mistral-7B-v0.2 using supervised fine-tuning.
Input Output 
Input Format:
[INST] {system_message}\n{instruction} [/INST]
Accepted Modalities:
text
Output Format:
Text generation
LLM NameJanus 7B
Repository 🤗https://huggingface.co/kaist-ai/janus-7b 
Base Model(s)  alpindale/Mistral-7B-v0.2-hf   alpindale/Mistral-7B-v0.2-hf
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintainerkaist-ai
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   0.0 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Janus 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
MegaBeam Mistral 7B 512K512K / 14.4 GB568150
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB563316
Hebrew Mistral 7B 200K256K / 30 GB1461915
Astral 256K 7B V2250K / 14.4 GB70
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than kaist-ai/janus-7b.

Rank the Janus 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? 43470 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 v20241227
  Support LLM Explorer