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

AlphaMonarch Dora by abideen

 »  All LLMs  »  abideen  »  AlphaMonarch Dora   URL Share it on

  41   
  Autotrain compatible Base model:finetune:mlabonne/n... Base model:mlabonne/neuralmona...   Chatml   Conversational Dataset:argilla/openhermes2.5-...   Distillation   En   Endpoints compatible   Finetuned   Generated from trainer   Gpt4   Instruct   Mistral   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/abideen/AlphaMonarch-dora 

AlphaMonarch Dora Benchmarks

ARC: 73.21 vs 96.7 (so35)-24.3%
HellaSwag: 89.26 vs 95.3 (gpt4)-6.3%
MMLU: 64.47 vs 88.3 (so35)-27%
TruthfulQA: 78.02 vs 59 (gpt4)32.2%
WinoGrande: 84.45 vs 87.5 (gpt4)-3.5%
GSM8K: 65.73 vs 96.4 (so35)-31.8%
LLME Score: 0.18594
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
AlphaMonarch Dora (abideen/AlphaMonarch-dora)

AlphaMonarch Dora Parameters and Internals

Model Type 
text-generation
Additional Notes 
All hyperparameters were kept consistent across all these experiments.
Supported Languages 
en (primary)
Training Details 
Data Sources:
argilla/OpenHermes2.5-dpo-binarized-alpha
Methodology:
DPO fine-tuning using DoRA
LLM NameAlphaMonarch Dora
Repository 🤗https://huggingface.co/abideen/AlphaMonarch-dora 
Base Model(s)  NeuralMonarch 7B   mlabonne/NeuralMonarch-7B
Model Size7b
Required VRAM14.4 GB
Updated2024-12-22
Maintainerabideen
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.39.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the AlphaMonarch Dora

Model
Likes
Downloads
VRAM
BetaMonarch 10.7B23521 GB

Best Alternatives to AlphaMonarch Dora

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB26689
MegaBeam Mistral 7B 512K512K / 14.4 GB711346
SpydazWeb AI HumanAI RP512K / 14.4 GB261
SpydazWeb AI HumanAI 002512K / 14.4 GB191
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB328215
Hebrew Mistral 7B 200K256K / 30 GB319315
Astral 256K 7B V2250K / 14.4 GB190
Astral 256K 7B250K / 14.4 GB160
Boptruth Agatha 7B128K / 14.4 GB4750
Note: green Score (e.g. "73.2") means that the model is better than abideen/AlphaMonarch-dora.

Rank the AlphaMonarch Dora 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? 40123 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 v20241217
  Support LLM Explorer