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

Turdus by udkai

 »  All LLMs  »  udkai  »  Turdus   URL Share it on

  60   
  7b   Autotrain compatible Base model:finetune:mlabonne/n... Base model:mlabonne/neuralmarc... Dataset:hromi/winograd dpo bas...   Doi:10.57967/hf/1611   Dpo   Endpoints compatible   Mistral   Mlabonne/neuralmarcoro14-7b   Mmlu abstract algebra   Region:us   Safetensors   Sharded   Tensorflow   Winograd
Model Card on HF 🤗: https://huggingface.co/udkai/Turdus 

Turdus Benchmarks

ARC: 73.38 vs 96.7 (so35)-24.1%
HellaSwag: 88.56 vs 95.3 (gpt4)-7.1%
MMLU: 64.52 vs 88.3 (so35)-26.9%
TruthfulQA: 67.11 vs 59 (gpt4)13.7%
WinoGrande: 86.66 vs 87.5 (gpt4)-1%
GSM8K: 67.7 vs 96.4 (so35)-29.8%
LLME Score: 0.17592
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Turdus (udkai/Turdus)

Turdus Parameters and Internals

Additional Notes 
Subtle DPO-Contamination with modified Winogrande increases TruthfulQA, Hellaswag & ARC compared to the base model.
Training Details 
Data Sources:
hromi/winograd_dpo_basic
Methodology:
direct preference optimization
LLM NameTurdus
Repository 🤗https://huggingface.co/udkai/Turdus 
Base Model(s)  NeuralMarcoro14 7B   mlabonne/NeuralMarcoro14-7B
Model Size7b
Required VRAM14.4 GB
Updated2024-12-27
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
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Turdus

Model
Likes
Downloads
VRAM
Turdus GPTQ5314 GB

Best Alternatives to Turdus

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25749
MegaBeam Mistral 7B 512K512K / 14.4 GB681746
SpydazWeb AI HumanAI RP512K / 14.4 GB271
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB325815
Hebrew Mistral 7B 200K256K / 30 GB306115
Astral 256K 7B V2250K / 14.4 GB180
Astral 256K 7B250K / 14.4 GB150
Boptruth Agatha 7B128K / 14.4 GB4610
Note: green Score (e.g. "73.2") means that the model is better than udkai/Turdus.

Rank the Turdus 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? 40304 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