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

MixTAO 7Bx2 MoE V8.1 by zhengr

 »  All LLMs  »  zhengr  »  MixTAO 7Bx2 MoE V8.1   URL Share it on

  8760   

MixTAO 7Bx2 MoE V8.1 is an open-source language model by zhengr. Features: 12.9b LLM, VRAM: 25.8GB, Context: 32K, License: apache-2.0, MoE, HF Score: 77.5, LLM Explorer Score: 0.21, Arc: 73.8, HellaSwag: 89.2, MMLU: 64.9, TruthfulQA: 78.6, WinoGrande: 87.4, GSM8K: 71.1.

  Autotrain compatible   Conversational   Endpoints compatible   Mixtral   Model-index   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1 

MixTAO 7Bx2 MoE V8.1 Benchmarks

MMLU Pro: 20.52
GPQA: 6.49
MUSR: 8.3
BBH: 19.18
IFEval: 41.88 vs 88 (so35)-52.4%
ARC: 73.81 vs 96.7 (so35)-23.7%
HellaSwag: 89.22 vs 95.3 (gpt4)-6.4%
MMLU: 64.92 vs 88.3 (so35)-26.5%
TruthfulQA: 78.57 vs 59 (gpt4)33.2%
WinoGrande: 87.37 vs 87.5 (gpt4)-0.1%
GSM8K: 71.11 vs 96.4 (so35)-26.2%
MATH Lvl 5: 6.04
LLME Score: 0.2142
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MixTAO 7Bx2 MoE V8.1 (zhengr/MixTAO-7Bx2-MoE-v8.1)
🌟 Advertise your project 🚀

MixTAO 7Bx2 MoE V8.1 Parameters and Internals

Model Type 
MoE, text generation
Additional Notes 
MixTAO-7Bx2-MoE is a Mixture of Experts model mainly used for large model technology experiments.
Input Output 
Input Format:
Alpaca Prompt Template
Accepted Modalities:
text
Output Format:
Text response
LLM NameMixTAO 7Bx2 MoE V8.1
Repository 🤗https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1 
Model Size12.9b
Required VRAM25.8 GB
Updated2024-09-16
Maintainerzhengr
Model Typemixtral
Model Files  1.9 GB: 1-of-13   2.0 GB: 2-of-13   2.0 GB: 3-of-13   2.0 GB: 4-of-13   1.9 GB: 5-of-13   2.0 GB: 6-of-13   2.0 GB: 7-of-13   2.0 GB: 8-of-13   2.0 GB: 9-of-13   2.0 GB: 10-of-13   2.0 GB: 11-of-13   2.0 GB: 12-of-13   2.0 GB: 13-of-13
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the MixTAO 7Bx2 MoE V8.1

Model
Likes
Downloads
VRAM
MixTAO 7Bx2 MoE V8.1 GGUF102044 GB

Best Alternatives to MixTAO 7Bx2 MoE V8.1

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 7Bx2 MoE V8.132K / 25.8 GB1929855
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB101
LogoS 7Bx2 MoE 13B V0.232K / 25.9 GB769110
MultiMash8 13B Slerp32K / 25.7 GB50
MultiMash11 13B Slerp32K / 25.7 GB90
MultiMash9 13B Slerp32K / 25.7 GB50
MultiMash10 13B Slerp32K / 25.7 GB80
Multimash3 12B Slerp32K / 25.7 GB80
MixTaoTruthful 13B Slerp32K / 25.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than zhengr/MixTAO-7Bx2-MoE-v8.1.

Rank the MixTAO 7Bx2 MoE V8.1 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer