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

Qwen Orpo V1 by FINGU-AI

 »  All LLMs  »  FINGU-AI  »  Qwen Orpo V1   URL Share it on

  70   
  Autotrain compatible Base model:finetune:qwen/qwen1... Base model:qwen/qwen1.5-0.5b-c...   Conversational   Endpoints compatible   Orpo   Qwen2   Region:us   Safetensors   Trl
Model Card on HF 🤗: https://huggingface.co/FINGU-AI/Qwen-Orpo-v1 

Qwen Orpo V1 Benchmarks

ARC: 31.14 vs 96.7 (so35)-67.8%
HellaSwag: 44.58 vs 95.3 (gpt4)-53.2%
MMLU: 33.73 vs 88.3 (so35)-61.8%
TruthfulQA: 42.59 vs 59 (gpt4)-27.8%
WinoGrande: 57.06 vs 87.5 (gpt4)-34.8%
GSM8K: 8.57 vs 96.4 (so35)-91.1%
LLME Score: 0.23016
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen Orpo V1 (FINGU-AI/Qwen-Orpo-v1)

Qwen Orpo V1 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
finance, investment, legal frameworks
Applications:
investment banking, corporate finance, asset management, regulatory compliance
Supported Languages 
English (Proficient), Korean (Proficient), Japanese (Proficient)
Training Details 
Data Volume:
28k training samples
Methodology:
Fine-tuned using ORPO fine-tuning through the TrL Library and Transformer
LLM NameQwen Orpo V1
Repository 🤗https://huggingface.co/FINGU-AI/Qwen-Orpo-v1 
Base Model(s)  Qwen/Qwen1.5-0.5B-Chat   Qwen/Qwen1.5-0.5B-Chat
Model Size0.5b
Required VRAM0.9 GB
Updated2025-02-22
MaintainerFINGU-AI
Model Typeqwen2
Model Files  0.9 GB   0.0 GB
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size151646
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen Orpo V1

Best Alternatives
Context / RAM
Downloads
Likes
Reader Lm 0.5B250K / 1 GB450135
Qwen2 0.5B128K / 1 GB623886134
...PRYMMAL 0.5B FT V4 MUSR Mathis128K / 1 GB621
...0.5B FT EnhancedMUSREnsembleV3128K / 1 GB321
....5B FT V4 MUSR ENSEMBLE Mathis128K / 2 GB301
...0.5B FT MUSR ENSEMBLE V2Mathis128K / 1 GB250
ECE PRYMMAL 0.5B FT V3 MUSR128K / 2 GB670
ECE PRYMMAL 0.5B FT V4 MUSR128K / 2 GB680
Qwen2 0.5B128K / 1 GB55703
ECE PRYMMAL0.5B Youri128K / 1.3 GB31
Note: green Score (e.g. "73.2") means that the model is better than FINGU-AI/Qwen-Orpo-v1.

Rank the Qwen Orpo V1 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? 43470 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