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

Twilight Miqu 146B by softwareweaver

 »  All LLMs  »  softwareweaver  »  Twilight Miqu 146B   URL Share it on

  16   
  Merged Model   Autotrain compatible Base model:jukofyork/dark-miqu... Base model:sophosympatheia/mid...   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/softwareweaver/Twilight-Miqu-146B 

Twilight Miqu 146B Benchmarks

LLME Score: 0.19021
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Twilight Miqu 146B (softwareweaver/Twilight-Miqu-146B)

Twilight Miqu 146B Parameters and Internals

Model Type 
story writing
Additional Notes 
This merge comes with no warranties or guarantees. It uses leaked weights and has inherent risks.
LLM NameTwilight Miqu 146B
Repository 🤗https://huggingface.co/softwareweaver/Twilight-Miqu-146B 
Base Model(s)  Dark Miqu 70B   sophosympatheia/Midnight-Miqu-70B-v1.5   Dawn Miqu 70B   jukofyork/Dark-Miqu-70B   sophosympatheia/Midnight-Miqu-70B-v1.5   jukofyork/Dawn-Miqu-70B
Merged ModelYes
Model Size70b
Required VRAM219.2 GB
Updated2025-02-22
Maintainersoftwareweaver
Model Typellama
Model Files  4.9 GB: 1-of-61   4.7 GB: 2-of-61   5.0 GB: 3-of-61   5.0 GB: 4-of-61   5.0 GB: 5-of-61   5.0 GB: 6-of-61   5.0 GB: 7-of-61   5.0 GB: 8-of-61   4.6 GB: 9-of-61   4.7 GB: 10-of-61   4.7 GB: 11-of-61   5.0 GB: 12-of-61   4.8 GB: 13-of-61   5.0 GB: 14-of-61   4.8 GB: 15-of-61   5.0 GB: 16-of-61   4.8 GB: 17-of-61   5.0 GB: 18-of-61   4.8 GB: 19-of-61   4.7 GB: 20-of-61   4.8 GB: 21-of-61   5.0 GB: 22-of-61   4.8 GB: 23-of-61   5.0 GB: 24-of-61   4.8 GB: 25-of-61   4.8 GB: 26-of-61   4.7 GB: 27-of-61   5.0 GB: 28-of-61   4.8 GB: 29-of-61   5.0 GB: 30-of-61   4.8 GB: 31-of-61   4.8 GB: 32-of-61   5.0 GB: 33-of-61   4.7 GB: 34-of-61   5.0 GB: 35-of-61   5.0 GB: 36-of-61   5.0 GB: 37-of-61   5.0 GB: 38-of-61   5.0 GB: 39-of-61   5.0 GB: 40-of-61   4.6 GB: 41-of-61   4.7 GB: 42-of-61   4.7 GB: 43-of-61   4.7 GB: 44-of-61   5.0 GB: 45-of-61
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length32764
Model Max Length32764
Transformers Version4.41.1
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Twilight Miqu 146B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB25245
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB199121
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18655
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB3212
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB653
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB120
Yi 70B 200K RPMerge Franken195K / 142.4 GB101
Note: green Score (e.g. "73.2") means that the model is better than softwareweaver/Twilight-Miqu-146B.

Rank the Twilight Miqu 146B 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? 43470 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