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

SmartQwen1.5 1.8B Orpo V1 by vihangd

 »  All LLMs  »  vihangd  »  SmartQwen1.5 1.8B Orpo V1   URL Share it on

  5   
  Autotrain compatible Base model:finetune:vihangd/sm... Base model:vihangd/smartqwen1....   Conversational   Endpoints compatible   Generated from trainer   Orpo   Qwen2   Region:us   Safetensors   Trl

SmartQwen1.5 1.8B Orpo V1 Benchmarks

ARC: 36.09 vs 96.7 (so35)-62.7%
HellaSwag: 62.3 vs 95.3 (gpt4)-34.6%
MMLU: 43.06 vs 88.3 (so35)-51.2%
TruthfulQA: 39.82 vs 59 (gpt4)-32.5%
WinoGrande: 57.38 vs 87.5 (gpt4)-34.4%
GSM8K: 12.13 vs 96.4 (so35)-87.4%
LLME Score: 0.24644
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

SmartQwen1.5 1.8B Orpo V1 Parameters and Internals

LLM NameSmartQwen1.5 1.8B Orpo V1
Repository 🤗https://huggingface.co/vihangd/SmartQwen1.5-1.8B-orpo-v1 
Base Model(s)  vihangd/SmartQwen1.5-1.8B-v1   vihangd/SmartQwen1.5-1.8B-v1
Model Size1.8b
Required VRAM3.7 GB
Updated2024-09-12
Maintainervihangd
Model Typeqwen2
Model Files  3.7 GB   0.0 GB
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace
SmartQwen1.5 1.8B Orpo V1 (vihangd/SmartQwen1.5-1.8B-orpo-v1)

Best Alternatives to SmartQwen1.5 1.8B Orpo V1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 1.8B32K / 3.7 GB87338543
Qwen1.5 1.8B Chat32K / 3.7 GB2445044
Orca 2.0 Tau 1.8B32K / 3.7 GB2128
Qwen1.5 1.8B Seed Sft32K / 3.7 GB50
Neural Chat Mini V2.2 1.8B32K / 3.7 GB315
Sailor 1.8B Chat32K / 3.7 GB5594
Qwen1.5 Wukong 1.8B32K / 3.7 GB24
Hercules Mini 1.8B32K / 3.7 GB687
Coder1.8 ORPO TEST32K / 3.7 GB12
Tau 1.8B32K / 3.7 GB6412
Note: green Score (e.g. "73.2") means that the model is better than vihangd/SmartQwen1.5-1.8B-orpo-v1.

Rank the SmartQwen1.5 1.8B 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? 35926 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 v2024072803
  Support LLM Explorer