Midnight Miqu 103B V1.0 by sophosympatheia

 ยป  All LLMs  ยป  sophosympatheia  ยป  Midnight Miqu 103B V1.0   URL Share it on

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

Midnight Miqu 103B 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").
Midnight Miqu 103B V1.0 (sophosympatheia/Midnight-Miqu-103B-v1.0)

Midnight Miqu 103B V1.0 Parameters and Internals

Additional Notes 
The model is based on Miqu and supports 32K context length. It was created using the passthrough merge method.
LLM NameMidnight Miqu 103B V1.0
Repository ๐Ÿค—https://huggingface.co/sophosympatheia/Midnight-Miqu-103B-v1.0 
Merged ModelYes
Model Size103b
Required VRAM206.4 GB
Updated2025-06-01
Maintainersophosympatheia
Model Typellama
Model Files  9.6 GB: 1-of-21   10.0 GB: 2-of-21   9.9 GB: 3-of-21   10.0 GB: 4-of-21   9.8 GB: 5-of-21   9.9 GB: 6-of-21   9.8 GB: 7-of-21   9.7 GB: 8-of-21   10.0 GB: 9-of-21   9.9 GB: 10-of-21   9.8 GB: 11-of-21   9.9 GB: 12-of-21   9.7 GB: 13-of-21   9.8 GB: 14-of-21   9.8 GB: 15-of-21   9.8 GB: 16-of-21   9.8 GB: 17-of-21   10.0 GB: 18-of-21   9.9 GB: 19-of-21   9.8 GB: 20-of-21   9.5 GB: 21-of-21
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length32764
Model Max Length32764
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Midnight Miqu 103B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Dark Miqu 103B31K / 206.4 GB302
Midnight Miqu 103B V1.531K / 206.4 GB4019
BigWeave V15 103B31K / 206.6 GB142
OmegaDolphin 103B V0.14K / 175.6 GB151
Midnight Rose 103B V2.0.34K / 206.6 GB269
KitchenSink 103b4K / 178.6 GB179
Midnight Rose 103B V1.04K / 206.6 GB113
Aurora Nights 103B V1.04K / 206.6 GB1614
Rogue Rose 103B V0.24K / 206.5 GB3832
Lila 103B L24K / 206.2 GB00
Note: green Score (e.g. "73.2") means that the model is better than sophosympatheia/Midnight-Miqu-103B-v1.0.

Rank the Midnight Miqu 103B 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? 47770 in total.

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