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

Qwen1.5 0.5B Chat ORCA EPFL CDPO by attention-avengers

 »  All LLMs  »  attention-avengers  »  Qwen1.5 0.5B Chat ORCA EPFL CDPO   URL Share it on

  9   
  Adapter Base model:adapter:qwen/qwen1.... Base model:qwen/qwen1.5-0.5b-c...   Chat   Conversational   En   Finetuned   Lora   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/attention-avengers/Qwen1.5-0.5B-Chat-ORCA-EPFL-cDPO 

Qwen1.5 0.5B Chat ORCA EPFL CDPO Benchmarks

LLME Score: 0.18904
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 0.5B Chat ORCA EPFL CDPO (attention-avengers/Qwen1.5-0.5B-Chat-ORCA-EPFL-cDPO)

Qwen1.5 0.5B Chat ORCA EPFL CDPO Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model aims to fine-tune the base model to accurately answer open-ended and multiple-choice questions from various EPFL courses and the Orca Math dataset consisting of approximately 200K grade school math word problems.
Supported Languages 
en (High)
Training Details 
Data Sources:
microsoft/orca-math-word-problems-200k, EPFL dataset (not publicly available)
Methodology:
cDPO with bf16 mixed precision
LLM NameQwen1.5 0.5B Chat ORCA EPFL CDPO
Repository 🤗https://huggingface.co/attention-avengers/Qwen1.5-0.5B-Chat-ORCA-EPFL-cDPO 
Base Model(s)  Qwen/Qwen1.5-0.5B-Chat   Qwen/Qwen1.5-0.5B-Chat
Model Size0.5b
Required VRAM0 GB
Updated2025-02-22
Maintainerattention-avengers
Model Files  0.0 GB
Supported Languagesen
Model ArchitectureAdapter
Model Max Length32768
Is Biasednone
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj|down_proj|o_proj|k_proj|up_proj|gate_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16
Errorsreplace

Best Alternatives to Qwen1.5 0.5B Chat ORCA EPFL CDPO

Best Alternatives
Context / RAM
Downloads
Likes
...PRYMMAL 0.5B FT V4 MUSR Mathis128K / 1 GB221
Qwen Qwen1.5 0.5B 17198985250K / 0 GB50
Qwen Qwen1.5 0.5B 17198610460K / 0 GB70
Qwen Qwen1.5 0.5B 17198589720K / 0 GB60
Qwen Qwen1.5 0.5B 17198348800K / 0 GB60
Qwen Qwen1.5 0.5B 17197061050K / 0 GB60
Qwen Qwen1.5 0.5B 17197083530K / 0 GB60
Qwen Qwen1.5 0.5B 17197057450K / 0 GB60
Qwen Qwen1.5 0.5B 17197086940K / 0 GB60
Qwen Qwen1.5 0.5B 17196920020K / 0 GB60
Note: green Score (e.g. "73.2") means that the model is better than attention-avengers/Qwen1.5-0.5B-Chat-ORCA-EPFL-cDPO.

Rank the Qwen1.5 0.5B Chat ORCA EPFL CDPO 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