DoubleBagel 57B V1.0 by TeeZee

 ยป  All LLMs  ยป  TeeZee  ยป  DoubleBagel 57B V1.0   URL Share it on

  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

DoubleBagel 57B V1.0 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DoubleBagel 57B V1.0 (TeeZee/DoubleBagel-57B-v1.0)

DoubleBagel 57B V1.0 Parameters and Internals

Additional Notes 
The model was created by merging pre-trained language models using Mergekit with a specific YAML configuration associated with the merge method and the use of float32 and bfloat16. The configuration includes slices and scaling parameters.
Training Details 
Methodology:
Merged using the passthrough merge method
LLM NameDoubleBagel 57B V1.0
Repository ๐Ÿค—https://huggingface.co/TeeZee/DoubleBagel-57B-v1.0 
Merged ModelYes
Model Size57b
Required VRAM114.1 GB
Updated2025-01-22
MaintainerTeeZee
Model Typellama
Model Files  5.0 GB: 1-of-24   5.0 GB: 2-of-24   4.8 GB: 3-of-24   5.0 GB: 4-of-24   4.8 GB: 5-of-24   4.8 GB: 6-of-24   5.0 GB: 7-of-24   4.8 GB: 8-of-24   4.8 GB: 9-of-24   5.0 GB: 10-of-24   4.8 GB: 11-of-24   4.8 GB: 12-of-24   5.0 GB: 13-of-24   4.8 GB: 14-of-24   4.8 GB: 15-of-24   5.0 GB: 16-of-24   4.8 GB: 17-of-24   4.8 GB: 18-of-24   5.0 GB: 19-of-24   4.8 GB: 20-of-24   4.8 GB: 21-of-24   5.0 GB: 22-of-24   4.8 GB: 23-of-24   1.9 GB: 24-of-24
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to DoubleBagel 57B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Kaiju A 57B195K / 114.7 GB845
Kyllene 57B V1.0195K / 113.3 GB1345

Rank the DoubleBagel 57B V1.0 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? 41728 in total.

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