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

MoE Merging by Cartinoe5930

 »  All LLMs  »  Cartinoe5930  »  MoE Merging   URL Share it on

  1214   
  Arxiv:1910.09700   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Cartinoe5930/MoE-Merging 

MoE Merging Benchmarks

ARC: 65.44 vs 96.7 (so35)-32.3%
HellaSwag: 84.58 vs 95.3 (gpt4)-11.2%
MMLU: 61.31 vs 88.3 (so35)-30.6%
TruthfulQA: 57.83 vs 59 (gpt4)-2%
WinoGrande: 77.66 vs 87.5 (gpt4)-11.2%
GSM8K: 54.21 vs 96.4 (so35)-43.8%
LLME Score: 0.19594
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MoE Merging (Cartinoe5930/MoE-Merging)

MoE Merging Parameters and Internals

LLM NameMoE Merging
Repository 🤗https://huggingface.co/Cartinoe5930/MoE-Merging 
Model Size24.2b
Required VRAM48.3 GB
Updated2025-02-05
MaintainerCartinoe5930
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-5   10.0 GB: 2-of-5   10.0 GB: 3-of-5   10.0 GB: 4-of-5   8.4 GB: 5-of-5
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to MoE Merging

Best Alternatives
Context / RAM
Downloads
Likes
Proto Athena 4x7B32K / 48.4 GB80
Proto Athena V0.2 4x7B32K / 48.4 GB50
...erges MoE 4x7b V10 Mixtralv0.332K / 48.3 GB80
Sixtyoneeighty 4x7B V132K / 48.3 GB520
MixtureofMerges MoE 4x7bRP V1132K / 48.3 GB81
...icon Mixtral87 Merged Torch21232K / 26.7 GB50
Eclipse Mistral 4x7b32K / 48.5 GB161
Kicon Mixtral87 Merged 4176632K / 26.7 GB50
Boundary Mistral 4x7b MoE32K / 48.7 GB1171
...x7b Quantized Portuguese Luana32K / 26.7 GB501
Note: green Score (e.g. "73.2") means that the model is better than Cartinoe5930/MoE-Merging.

Rank the MoE Merging 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? 42577 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