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 V2.0.3 by sophosympatheia

 »  All LLMs  »  sophosympatheia  »  Midnight Rose 103B V2.0.3   URL Share it on

  11   
  Merged Model   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-v2.0.3 

Midnight Rose 103B V2.0.3 Benchmarks

LLME Score: 0.15563
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 V2.0.3 (sophosympatheia/Midnight-Rose-103B-v2.0.3)

Midnight Rose 103B V2.0.3 Parameters and Internals

Model Type 
text generation, roleplaying, storytelling
Use Cases 
Areas:
roleplaying, storytelling
Considerations:
The model is uncensored and should be used according to applicable legal and ethical standards.
Additional Notes 
This model is designed specifically for roleplaying and storytelling but may work for other tasks.
Supported Languages 
en (high)
Input Output 
Accepted Modalities:
text
Performance Tips:
Recommended context is around 6144 tokens. Use Quadratic Sampling with values between 0.2 and 0.5. Experiment with Min-P values ranging from 0.05 to 0.9.
LLM NameMidnight Rose 103B V2.0.3
Repository 🤗https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v2.0.3 
Merged ModelYes
Model Size103b
Required VRAM206.6 GB
Updated2025-04-19
Maintainersophosympatheia
Model Typellama
Model Files  10.0 GB: 1-of-22   9.7 GB: 2-of-22   9.9 GB: 3-of-22   10.0 GB: 4-of-22   9.6 GB: 5-of-22   9.8 GB: 6-of-22   9.8 GB: 7-of-22   9.8 GB: 8-of-22   9.6 GB: 9-of-22   9.7 GB: 10-of-22   9.7 GB: 11-of-22   9.8 GB: 12-of-22   10.0 GB: 13-of-22   9.9 GB: 14-of-22   9.9 GB: 15-of-22   9.8 GB: 16-of-22   10.0 GB: 17-of-22   9.7 GB: 18-of-22   9.8 GB: 19-of-22   9.8 GB: 20-of-22   9.8 GB: 21-of-22   0.5 GB: 22-of-22
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 V2.0.3

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
KitchenSink 103b4K / 178.6 GB29
Midnight Rose 103B V1.04K / 206.6 GB163
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-v2.0.3.

Rank the Midnight Rose 103B V2.0.3 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