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

Notus 7B V1 by argilla

 »  All LLMs  »  argilla  »  Notus 7B V1   URL Share it on

  7657   
  Autotrain compatible Base model:alignment-handbook/... Base model:finetune:alignment-...   Conversational Dataset:argilla/ultrafeedback-...   Dpo   En   Endpoints compatible   Mistral   Model-index   Preference   Region:us   Rlaif   Safetensors   Sharded   Tensorboard   Tensorflow   Ultrafeedback
Model Card on HF 🤗: https://huggingface.co/argilla/notus-7b-v1 

Notus 7B V1 Benchmarks

MMLU Pro: 22.26
GPQA: 5.26
MUSR: 6.59
BBH: 22.75
IFEval: 50.82 vs 88 (so35)-42.3%
ARC: 80.4 vs 96.7 (so35)-16.9%
HellaSwag: 58.5 vs 95.3 (gpt4)-38.6%
MMLU: 61.8 vs 88.3 (so35)-30%
TruthfulQA: 54.37 vs 59 (gpt4)-7.8%
WinoGrande: 79.4 vs 87.5 (gpt4)-9.3%
GSM8K: 39.9 vs 96.4 (so35)-58.6%
OpenCompas: 45.3 vs 73.3 (gpt4)-38.2%
Exam: 62.2 vs 77.2 (gpt4)-19.4%
Language: 21.1 vs 62 (gpt4)-66%
Knowledge: 48.4 vs 73.5 (gpt4)-34.1%
Understand: 50.5 vs 70 (gpt4)-27.9%
Reasoning: 44.7 vs 74.4 (gpt4)-39.9%
MATH Lvl 5: 3.17
LLME Score: 0.26369
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Notus 7B V1 (argilla/notus-7b-v1)

Notus 7B V1 Parameters and Internals

Model Type 
GPT-like, text-generation
Supported Languages 
English (Mainly)
Training Details 
Data Sources:
github.com/argilla-io/distilabel, openbmb/UltraFeedback
Methodology:
Direct Preference Optimization (DPO) fine-tuning
Hardware Used:
8 x A100 40GB
LLM NameNotus 7B V1
Repository 🤗https://huggingface.co/argilla/notus-7b-v1 
Base Model(s)  Zephyr 7B Sft Full   alignment-handbook/zephyr-7b-sft-full
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintainerargilla
Model Typemistral
Model Files  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
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Notus 7B V1

Model
Likes
Downloads
VRAM
Notus 7B V1 GGUF01622 GB
Notus 7B V1 GGUF234533 GB
Notus 7B V1 AWQ3864 GB
Notus 7B V1 GPTQ2214 GB

Best Alternatives to Notus 7B V1

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 argilla/notus-7b-v1.

Rank the Notus 7B V1 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