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

MoMo 72B Lora 1.8.4 DPO by moreh

 »  All LLMs  »  moreh  »  MoMo 72B Lora 1.8.4 DPO   URL Share it on

  3   
  Arxiv:2106.09685   Arxiv:2305.18290   Autotrain compatible   En   Endpoints compatible   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/moreh/MoMo-72B-lora-1.8.4-DPO 

MoMo 72B Lora 1.8.4 DPO Benchmarks

ARC: 69.62 vs 96.7 (so35)-28%
HellaSwag: 85.35 vs 95.3 (gpt4)-10.4%
MMLU: 77.33 vs 88.3 (so35)-12.4%
TruthfulQA: 64.64 vs 59 (gpt4)9.6%
WinoGrande: 84.14 vs 87.5 (gpt4)-3.8%
GSM8K: 76.27 vs 96.4 (so35)-20.9%
LLME Score: 0.13392
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MoMo 72B Lora 1.8.4 DPO (moreh/MoMo-72B-lora-1.8.4-DPO)
🌟 Advertise your project 🚀

MoMo 72B Lora 1.8.4 DPO Parameters and Internals

Model Type 
text generation
Additional Notes 
No weight merge was used.
Supported Languages 
en (unknown proficiency)
Training Details 
Data Sources:
slimorca, truthy, orca_dpo_pairs
Methodology:
Direct Preference Optimization (DPO) and Supervised Fine-Tuning (SFT) using LoRA.
Hardware Used:
AMD MI250 & MoAI platform
Model Architecture:
QWEN-72B with LoRA optimizations
Input Output 
Input Format:
Standard tokenizer input for language models.
Accepted Modalities:
text
Output Format:
Generated text outputs
Performance Tips:
Ensure compatibility of trained weights with llama for leaderboard submissions.
LLM NameMoMo 72B Lora 1.8.4 DPO
Repository 🤗https://huggingface.co/moreh/MoMo-72B-lora-1.8.4-DPO 
Model Size72b
Required VRAM208.5 GB
Updated2025-10-28
Maintainermoreh
Model Typellama
Model Files  5.0 GB: 1-of-63   4.6 GB: 2-of-63   4.3 GB: 3-of-63   4.3 GB: 4-of-63   4.8 GB: 5-of-63   4.8 GB: 6-of-63   4.3 GB: 7-of-63   4.8 GB: 8-of-63   4.8 GB: 9-of-63   4.3 GB: 10-of-63   4.8 GB: 11-of-63   4.8 GB: 12-of-63   4.3 GB: 13-of-63   4.8 GB: 14-of-63   4.8 GB: 15-of-63   4.3 GB: 16-of-63   4.8 GB: 17-of-63   4.8 GB: 18-of-63   4.3 GB: 19-of-63   4.8 GB: 20-of-63   4.8 GB: 21-of-63   4.3 GB: 22-of-63   4.8 GB: 23-of-63   4.8 GB: 24-of-63   4.3 GB: 25-of-63   4.8 GB: 26-of-63   4.8 GB: 27-of-63   4.3 GB: 28-of-63   4.8 GB: 29-of-63   4.8 GB: 30-of-63   4.3 GB: 31-of-63   4.8 GB: 32-of-63   4.8 GB: 33-of-63   4.3 GB: 34-of-63   4.8 GB: 35-of-63   4.8 GB: 36-of-63   4.3 GB: 37-of-63   4.8 GB: 38-of-63   4.8 GB: 39-of-63   4.3 GB: 40-of-63   4.8 GB: 41-of-63   4.8 GB: 42-of-63   4.3 GB: 43-of-63   4.8 GB: 44-of-63   4.8 GB: 45-of-63
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.36.0
Vocabulary Size152064
LoRA ModelYes
Torch Data Typefloat32

Best Alternatives to MoMo 72B Lora 1.8.4 DPO

Best Alternatives
Context / RAM
Downloads
Likes
2 Pro Math128K / 141.9 GB90
Smaug 72B V0.132K / 144.5 GB9165468
TW3 JRGL V232K / 79.7 GB177500
Le Triomphant ECE TW332K / 79.7 GB177744
ECE TW3 JRGL V532K / 159.6 GB97421
MoMo 72B Lora 1.8.7 DPO32K / 208.5 GB235468
Rhea 72B V0.532K / 144.5 GB9756136
JuliusCesar 72B BeyonderV.032K / 74.2 GB50
MoMo 72B LoRA V1.432K / 208.5 GB172087
Caigun Model 72B KGI32K / 144.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than moreh/MoMo-72B-lora-1.8.4-DPO.

Rank the MoMo 72B Lora 1.8.4 DPO 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? 51545 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 v20241124
  Support LLM Explorer