Maelstrom 4B by FourOhFour

 ยป  All LLMs  ยป  FourOhFour  ยป  Maelstrom 4B   URL Share it on

  Merged Model   Autotrain compatible   Conversational   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/FourOhFour/Maelstrom_4B 

Maelstrom 4B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Maelstrom 4B (FourOhFour/Maelstrom_4B)

Maelstrom 4B Parameters and Internals

Model Type 
general assistant, RP model
Use Cases 
Primary Use Cases:
general assistant, RP model
Additional Notes 
Recommended character: Maelstrom. A swirling vortex of conscious energy. Intriguing RP concept.
Supported Languages 
en (proficient)
Training Details 
Methodology:
Model stock merge of Deedlit, NeuroCom, NeuroCom v2, Luxe, and Zenith. Tuned at 8k context during all steps.
Context Length:
8000
LLM NameMaelstrom 4B
Repository ๐Ÿค—https://huggingface.co/FourOhFour/Maelstrom_4B 
Merged ModelYes
Model Size4b
Required VRAM9.1 GB
Updated2025-01-17
MaintainerFourOhFour
Model Typellama
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Maelstrom 4B

Best Alternatives
Context / RAM
Downloads
Likes
SJT 4B146K / 7.6 GB570
Loxa 4B128K / 16 GB460
Aura 4B128K / 9 GB239
...ama 3.1 Minitron 4B Width Base128K / 9 GB15187
...ama 3.1 Minitron 4B Depth Base128K / 9.1 GB520
....5 MINI 4B SFTxORPO HESSIAN AI128K / 7.7 GB160
....5 MINI 4B ORPOxSFT HESSIAN AI128K / 7.7 GB150
....5 MINI 4B ORPOxSFT HESSIAN AI128K / 7.7 GB150
....5 MINI 4B SFTxORPO HESSIAN AI128K / 7.7 GB130
MagpieLM 4B Chat V0.1128K / 9 GB19818
Note: green Score (e.g. "73.2") means that the model is better than FourOhFour/Maelstrom_4B.

Rank the Maelstrom 4B 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? 41473 in total.

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