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

Garrulus AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Garrulus AWQ   URL Share it on

  9   
  4-bit   7b   Autotrain compatible   Awq Base model:quantized:udkai/gar...   Base model:udkai/garrulus Dataset:hromi/winograd dpo bas...   Dpo   Mistral   Mlabonne/neuralmarcoro14-7b   Quantized   Region:us   Safetensors   Winograd
Model Card on HF 🤗: https://huggingface.co/TheBloke/Garrulus-AWQ 

Garrulus AWQ Benchmarks

LLME Score: 0.16082
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Garrulus AWQ (TheBloke/Garrulus-AWQ)

Garrulus AWQ Parameters and Internals

Model Type 
mistral
Additional Notes 
This model was initially named 'ContaminatedWine' but was later named 'Garrulus' after an encounter with a eurasian jay. The model shows improved performance not only on Winogrande but also on TruthfulQA, HellaSwag, and ARC challenge metrics due to DPO contamination with Winogrande.
Training Details 
Data Sources:
mlabonne/NeuralMarcoro14-7B, hromi/winograd_dpo_basic
Methodology:
Intentionally contaminated with two epochs of direct preference optimization (DPO) with a slightly modified Winogrande dataset.
Training Time:
Few minutes on a A40
Hardware Used:
Hardware of Berlin University of the Arts (UDK-berlin)
LLM NameGarrulus AWQ
Repository 🤗https://huggingface.co/TheBloke/Garrulus-AWQ 
Model NameGarrulus
Model CreatorUDK dot AI
Base Model(s)  Garrulus   udkai/Garrulus
Model Size1.2b
Required VRAM4.2 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Garrulus AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Feedback Wizard 4bit AWQ32K / 4.2 GB230
Quantized Kheopss AWQ 4bits V132K / 4.2 GB170
Ryze AWQ 4bit32K / 4.2 GB80
...lot Engine Step Json Short AWQ32K / 4.2 GB770
...V3 Plot Chat Roleplay Chat AWQ32K / 4.2 GB770
Dictalm2.0 Instruct AWQ32K / 4.2 GB3690
Dictalm2.0 AWQ32K / 4.2 GB3820
MistralLite AWQ32K / 4.2 GB83
LemonadeRP 4.5.3 AWQ32K / 4.2 GB770
SFR Embedding Mistral AWQ32K / 4.2 GB160
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Garrulus-AWQ.

Rank the Garrulus AWQ 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