Pygmalion 2 13B SuperCOT EXL2 by royallab

 ยป  All LLMs  ยป  royallab  ยป  Pygmalion 2 13B SuperCOT EXL2   URL Share it on

  Autotrain compatible   En   Endpoints compatible   Exl2   Llama   Quantized   Region:us

Pygmalion 2 13B SuperCOT EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pygmalion 2 13B SuperCOT EXL2 (royallab/Pygmalion-2-13b-SuperCOT-exl2)

Pygmalion 2 13B SuperCOT EXL2 Parameters and Internals

Additional Notes 
This is a quantized version of the base model with branches for different bits per weight.
LLM NamePygmalion 2 13B SuperCOT EXL2
Repository ๐Ÿค—https://huggingface.co/royallab/Pygmalion-2-13b-SuperCOT-exl2 
Base Model(s)  Pygmalion 2 13B SuperCOT2   royallab/Pygmalion-2-13b-SuperCOT2
Model Size13b
Required VRAM6.8 GB
Updated2024-12-26
Maintainerroyallab
Model Typellama
Model Files  6.8 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.34.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Pygmalion 2 13B SuperCOT EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB250
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB201
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB181
WhiteRabbitNeo 13B V116K / 26 GB1652405
CodeLlama 13B Python Fp1616K / 26 GB148125
CodeLlama 13B Instruct Fp1616K / 26 GB193129
CodeLlama 13B Fp1616K / 26 GB1866
Codellama 13B Bnb 4bit16K / 7.2 GB911
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB472
Trinity 13B16K / 26 GB2615
Note: green Score (e.g. "73.2") means that the model is better than royallab/Pygmalion-2-13b-SuperCOT-exl2.

Rank the Pygmalion 2 13B SuperCOT EXL2 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? 40303 in total.

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