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

Nimbus Miqu V0.1 70B by invisietch

 »  All LLMs  »  invisietch  »  Nimbus Miqu V0.1 70B   URL Share it on

  34   
  Merged Model   Autotrain compatible   Conversational   En   Endpoints compatible   Llama   Model-index   Not-for-all-audiences   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/invisietch/Nimbus-Miqu-v0.1-70B 

Nimbus Miqu V0.1 70B Benchmarks

MMLU Pro: 31.7
GPQA: 11.86
MUSR: 9.33
BBH: 43.45
IFEval: 46.47 vs 88 (so35)-47.2%
MATH Lvl 5: 6.04
LLME Score: 0.27144
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nimbus Miqu V0.1 70B (invisietch/Nimbus-Miqu-v0.1-70B)

Nimbus Miqu V0.1 70B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
RP/creative writing
Limitations:
The model is fairly unaligned and can generate explicit, disturbing or offensive responses.
Additional Notes 
This model is an attempt to merge creativity and negative-capability from different models. It is primarily focused on creative writing and role-playing. The model can handle context lengths up to 32k tokens.
Input Output 
Input Format:
Alpaca, ChatML & Vicuna formats are supported.
Performance Tips:
The model prefers a longer response length. Recommended sampler settings include Temp: 0.75-0.95, Top-P: 0.95, Min-P: 0.02, Rep Pen: 1.09-1.12, Response Length: 350+.
LLM NameNimbus Miqu V0.1 70B
Repository 🤗https://huggingface.co/invisietch/Nimbus-Miqu-v0.1-70B 
Base Model(s)  crestf411/sunfall-midnight-miqu-v0.2-v1.5-70B   TheDrummer/Moist-Miqu-70B-v1.1   crestf411/sunfall-midnight-miqu-v0.2-v1.5-70B   TheDrummer/Moist-Miqu-70B-v1.1
Merged ModelYes
Model Size70b
Required VRAM137.9 GB
Updated2025-02-22
Maintainerinvisietch
Model Typellama
Model Files  7.9 GB: 1-of-18   7.8 GB: 2-of-18   7.6 GB: 3-of-18   7.8 GB: 4-of-18   7.6 GB: 5-of-18   7.8 GB: 6-of-18   7.6 GB: 7-of-18   7.8 GB: 8-of-18   7.6 GB: 9-of-18   7.8 GB: 10-of-18   7.6 GB: 11-of-18   7.8 GB: 12-of-18   7.6 GB: 13-of-18   7.8 GB: 14-of-18   7.6 GB: 15-of-18   7.8 GB: 16-of-18   7.6 GB: 17-of-18   6.8 GB: 18-of-18
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length32764
Model Max Length32764
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Nimbus Miqu V0.1 70B

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

Rank the Nimbus Miqu V0.1 70B 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