Qwen2 Simple Arguments by cris177

 ยป  All LLMs  ยป  cris177  ยป  Qwen2 Simple Arguments   URL Share it on

  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Gguf   Model-index   Quantized   Qwen2   Region:us   Safetensors

Qwen2 Simple Arguments Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 Simple Arguments (cris177/Qwen2-Simple-Arguments)

Qwen2 Simple Arguments Parameters and Internals

Model Type 
LLM
Supported Languages 
English (NLP)
Training Details 
Data Sources:
synthetic data based on various types of logical arguments
Data Volume:
50k arguments created for training and 100 for testing
Methodology:
The data was converted to the Alpaca chat format before feeding it into the model. We used unsloth for memory reduced sped up training. We trained for one epoch.
Training Time:
2.5 hours
Hardware Used:
Less than 2.5 GB of VRAM were used for training
LLM NameQwen2 Simple Arguments
Repository ๐Ÿค—https://huggingface.co/cris177/Qwen2-Simple-Arguments 
Model Size0.5b
Required VRAM0.4 GB
Updated2025-02-22
Maintainercris177
Model Typeqwen2
Model Files  1.0 GB   0.4 GB   1.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Type4bit|gguf
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.42.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 Simple Arguments

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 Coder 0.5B Merged32K / 1.3 GB1900
Qwen2 0.5B Instruct GGUF32K / 0.3 GB243101
Qwen2 0.5B Instruct GGUF32K / 0.3 GB1320
Qwen1.5 0.5B32K / 0.4 GB170
Qwen1.5 0.5B Chat GGUF32K / 0.3 GB2393
Qwen2 0.5B Bnb 4bit128K / 0.5 GB78362
Ymail Search Qwen2 0.5B 16bit128K / 1 GB610
....O.S.I.E.v4o 0.5B Stage1 Beta1128K / 1 GB591
Ymail Search Qwen2 0.5B 4bit128K / 0.5 GB130
....O.S.I.E.v4o 0.5B Stage1 Beta1128K / 1 GB51
Note: green Score (e.g. "73.2") means that the model is better than cris177/Qwen2-Simple-Arguments.

Rank the Qwen2 Simple Arguments Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227