LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Midnight Rose 103B V1.0 by sophosympatheia

 »  All LLMs  »  sophosympatheia  »  Midnight Rose 103B V1.0   URL Share it on

  16   
  Arxiv:2307.11760   Autotrain compatible   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v1.0 

Midnight Rose 103B V1.0 Benchmarks

LLME Score: 0.15006
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Midnight Rose 103B V1.0 (sophosympatheia/Midnight-Rose-103B-v1.0)

Midnight Rose 103B V1.0 Parameters and Internals

Model Type 
Roleplaying, Storytelling, Creative Writing
Use Cases 
Areas:
Roleplaying, Storytelling, Creative Writing
Primary Use Cases:
Roleplaying, Storytelling
Additional Notes 
The model is designed for creative writing and roleplaying; it may perform well in other tasks but hasn't been tested.
Supported Languages 
en (Proficient)
Training Details 
Context Length:
6144
Input Output 
Performance Tips:
Max context should be around 6144 tokens. Use Quadratic Sampling with smoothing factor between 0.2 and 0.5. Experiment with Min-P and other settings for optimal performance.
LLM NameMidnight Rose 103B V1.0
Repository 🤗https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v1.0 
Model Size103b
Required VRAM206.6 GB
Updated2025-04-19
Maintainersophosympatheia
Model Typellama
Model Files  9.6 GB: 1-of-21   9.9 GB: 2-of-21   10.0 GB: 3-of-21   9.7 GB: 4-of-21   9.8 GB: 5-of-21   9.8 GB: 6-of-21   10.0 GB: 7-of-21   10.0 GB: 8-of-21   9.8 GB: 9-of-21   9.8 GB: 10-of-21   9.8 GB: 11-of-21   9.8 GB: 12-of-21   9.9 GB: 13-of-21   9.7 GB: 14-of-21   10.0 GB: 15-of-21   10.0 GB: 16-of-21   9.8 GB: 17-of-21   9.6 GB: 18-of-21   10.0 GB: 19-of-21   9.8 GB: 20-of-21   9.8 GB: 21-of-21
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Midnight Rose 103B V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Dark Miqu 103B31K / 206.4 GB302
Midnight Miqu 103B V1.531K / 206.4 GB16918
BigWeave V15 103B31K / 206.6 GB32
Midnight Miqu 103B V1.031K / 206.4 GB3713
OmegaDolphin 103B V0.14K / 175.6 GB221
Midnight Rose 103B V2.0.34K / 206.6 GB119
KitchenSink 103b4K / 178.6 GB29
Aurora Nights 103B V1.04K / 206.6 GB514
Rogue Rose 103B V0.24K / 206.5 GB3631
Lila 103B L24K / 206.2 GB00
Note: green Score (e.g. "73.2") means that the model is better than sophosympatheia/Midnight-Rose-103B-v1.0.

Rank the Midnight Rose 103B V1.0 Capabilities

🆘 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! 🌟

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? 46490 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer