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

Miqu MS 70B by Undi95

 »  All LLMs  »  Undi95  »  Miqu MS 70B   URL Share it on

  5   
  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:152334h/miqu-1-70b-... Base model:migtissera/tess-70b... Base model:neversleep/miqumaid... Base model:sophosympatheia/mid...   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Undi95/Miqu-MS-70B 

Miqu MS 70B Benchmarks

ARC: 73.29 vs 96.7 (so35)-24.2%
HellaSwag: 88.63 vs 95.3 (gpt4)-7%
MMLU: 75.48 vs 88.3 (so35)-14.5%
TruthfulQA: 69.32 vs 59 (gpt4)17.5%
WinoGrande: 85.71 vs 87.5 (gpt4)-2%
GSM8K: 68.01 vs 96.4 (so35)-29.5%
LLME Score: 0.15127
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Miqu MS 70B (Undi95/Miqu-MS-70B)
🌟 Advertise your project 🚀

Miqu MS 70B Parameters and Internals

Model Type 
pre-trained language model
Additional Notes 
This model was created using a new merge method, Model Stock, to combine several pre-trained models with different prompt formats.
Input Output 
Input Format:
Supports multiple prompt formats (e.g., Alpaca, Mistral, Vicuna)
Output Format:
Dependent on specified prompt format
LLM NameMiqu MS 70B
Repository 🤗https://huggingface.co/Undi95/Miqu-MS-70B 
Base Model(s)  migtissera/Tess-70B-v1.6   Miqu 1 70B Sf   MiquMaid V2 70B   sophosympatheia/Midnight-Miqu-70B-v1.0   migtissera/Tess-70B-v1.6   152334H/miqu-1-70b-sf   NeverSleep/MiquMaid-v2-70B   sophosympatheia/Midnight-Miqu-70B-v1.0
Merged ModelYes
Model Size70b
Required VRAM138 GB
Updated2025-09-23
MaintainerUndi95
Model Typellama
Model Files  9.6 GB: 1-of-15   9.8 GB: 2-of-15   9.6 GB: 3-of-15   9.8 GB: 4-of-15   9.9 GB: 5-of-15   9.7 GB: 6-of-15   10.0 GB: 7-of-15   9.9 GB: 8-of-15   9.7 GB: 9-of-15   9.6 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.6 GB: 13-of-15   9.9 GB: 14-of-15   1.1 GB: 15-of-15
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length32764
Model Max Length32764
Transformers Version4.39.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Miqu MS 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB98265
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB13122
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB1023
...a 3 70B Instruct Gradient 262K256K / 141.9 GB11456
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB263
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB130
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB463
Yi 70B 200K RPMerge Franken195K / 142.4 GB61
Note: green Score (e.g. "73.2") means that the model is better than Undi95/Miqu-MS-70B.

Rank the Miqu MS 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? 51538 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 v20241124
  Support LLM Explorer