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

Garrulus by udkai

 »  All LLMs  »  udkai  »  Garrulus   URL Share it on

  13   
  7b   Autotrain compatible Base model:finetune:mlabonne/n... Base model:mlabonne/neuralmarc... Dataset:hromi/winograd dpo bas...   Doi:10.57967/hf/1590   Dpo   Endpoints compatible   Mistral   Mlabonne/neuralmarcoro14-7b   Region:us   Safetensors   Sharded   Tensorflow   Winograd
Model Card on HF 🤗: https://huggingface.co/udkai/Garrulus 

Garrulus Benchmarks

ARC: 73.29 vs 96.7 (so35)-24.2%
HellaSwag: 88.87 vs 95.3 (gpt4)-6.7%
MMLU: 64.57 vs 88.3 (so35)-26.9%
TruthfulQA: 68.23 vs 59 (gpt4)15.6%
WinoGrande: 91.48 vs 87.5 (gpt4)4.5%
GSM8K: 64.52 vs 96.4 (so35)-33.1%
LLME Score: 0.16649
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Garrulus (udkai/Garrulus)

Garrulus Parameters and Internals

Model Type 
CAUSAL_LM
Additional Notes 
The model has been intentionally contaminated with two epochs of DPO, leading to improved performance on the Winogrande dataset as well as other metrics like TruthfulQA, HellaSwag, and ARC challenge.
Training Details 
Data Sources:
hromi/winograd_dpo_basic
Methodology:
Direct Preference Optimization (DPO) with the Winograd dataset.
Hardware Used:
A40 GPU
LLM NameGarrulus
Repository 🤗https://huggingface.co/udkai/Garrulus 
Base Model(s)  NeuralMarcoro14 7B   mlabonne/NeuralMarcoro14-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
Maintainerudkai
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Garrulus

Model
Likes
Downloads
VRAM
Garrulus GGUF8852 GB
Garrulus GPTQ3184 GB
Garrulus AWQ294 GB

Best Alternatives to Garrulus

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
MegaBeam Mistral 7B 512K512K / 14.4 GB655449
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB647215
Hebrew Mistral 7B 200K256K / 30 GB489915
Astral 256K 7B V2250K / 14.4 GB60
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than udkai/Garrulus.

Rank the Garrulus 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? 42577 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