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

MultiMash8 13B Slerp by allknowingroger

 »  All LLMs  »  allknowingroger  »  MultiMash8 13B Slerp   URL Share it on

  26   
  Merged Model Allknowingroger/jupiterinex12-...   Autotrain compatible Base model:allknowingroger/jup... Base model:mixtao/mixtao-7bx2-...   Endpoints compatible   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow   Zhengr/mixtao-7bx2-moe-v8.1
Model Card on HF 🤗: https://huggingface.co/allknowingroger/MultiMash8-13B-slerp 

MultiMash8 13B Slerp Benchmarks

MMLU Pro: 23.62
GPQA: 5.15
MUSR: 14.5
BBH: 32.27
IFEval: 43.21 vs 88 (so35)-50.9%
MATH Lvl 5: 7.4
LLME Score: 0.25503
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MultiMash8 13B Slerp (allknowingroger/MultiMash8-13B-slerp)

MultiMash8 13B Slerp Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model is a merge using LazyMergekit technology.
LLM NameMultiMash8 13B Slerp
Repository 🤗https://huggingface.co/allknowingroger/MultiMash8-13B-slerp 
Base Model(s)  zhengr/MixTAO-7Bx2-MoE-v8.1   JupiterINEX12 12B MoE   zhengr/MixTAO-7Bx2-MoE-v8.1   allknowingroger/JupiterINEX12-12B-MoE
Merged ModelYes
Model Size12.9b
Required VRAM25.7 GB
Updated2025-01-17
Maintainerallknowingroger
Model Typemixtral
Model Files  1.0 GB: 1-of-28   0.9 GB: 2-of-28   1.0 GB: 3-of-28   0.9 GB: 4-of-28   0.9 GB: 5-of-28   0.9 GB: 6-of-28   0.9 GB: 7-of-28   0.9 GB: 8-of-28   1.0 GB: 9-of-28   0.9 GB: 10-of-28   0.9 GB: 11-of-28   0.9 GB: 12-of-28   0.9 GB: 13-of-28   0.9 GB: 14-of-28   1.0 GB: 15-of-28   0.9 GB: 16-of-28   0.9 GB: 17-of-28   0.9 GB: 18-of-28   0.9 GB: 19-of-28   0.9 GB: 20-of-28   1.0 GB: 21-of-28   0.9 GB: 22-of-28   0.9 GB: 23-of-28   0.9 GB: 24-of-28   0.9 GB: 25-of-28   0.9 GB: 26-of-28   1.0 GB: 27-of-28   0.8 GB: 28-of-28
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to MultiMash8 13B Slerp

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 7Bx2 MoE V8.132K / 25.8 GB940355
MixTAO 7Bx2 MoE V8.132K / 25.8 GB876052
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB50
LogoS 7Bx2 MoE 13B V0.232K / 25.9 GB368310
MultiMash9 13B Slerp32K / 25.7 GB240
MultiMash11 13B Slerp32K / 25.7 GB190
MultiMash10 13B Slerp32K / 25.7 GB240
Multimash3 12B Slerp32K / 25.7 GB270
MixTaoTruthful 13B Slerp32K / 25.7 GB170
Note: green Score (e.g. "73.2") means that the model is better than allknowingroger/MultiMash8-13B-slerp.

Rank the MultiMash8 13B Slerp 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? 41473 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