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

Mixtral 8x7B Instruct V0.1 Upscaled by Aratako

 »  All LLMs  »  Aratako  »  Mixtral 8x7B Instruct V0.1 Upscaled   URL Share it on

  29   
  Merged Model   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Conversational   De   En   Endpoints compatible   Es   Fr   Instruct   It   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Aratako/Mixtral-8x7B-Instruct-v0.1-upscaled 

Mixtral 8x7B Instruct V0.1 Upscaled Benchmarks

ARC: 69.71 vs 96.7 (so35)-27.9%
HellaSwag: 88.09 vs 95.3 (gpt4)-7.6%
MMLU: 71.03 vs 88.3 (so35)-19.6%
TruthfulQA: 67.35 vs 59 (gpt4)14.2%
WinoGrande: 81.06 vs 87.5 (gpt4)-7.4%
GSM8K: 54.28 vs 96.4 (so35)-43.7%
LLME Score: 0.18351
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 8x7B Instruct V0.1 Upscaled (Aratako/Mixtral-8x7B-Instruct-v0.1-upscaled)

Mixtral 8x7B Instruct V0.1 Upscaled Parameters and Internals

Supported Languages 
fr (supported), it (supported), de (supported), es (supported), en (supported)
LLM NameMixtral 8x7B Instruct V0.1 Upscaled
Repository 🤗https://huggingface.co/Aratako/Mixtral-8x7B-Instruct-v0.1-upscaled 
Base Model(s)  mistralai/Mixtral-8x7B-Instruct-v0.1   mistralai/Mixtral-8x7B-Instruct-v0.1
Merged ModelYes
Model Size81.5b
Required VRAM162.9 GB
Updated2025-02-22
MaintainerAratako
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-17   9.9 GB: 2-of-17   9.9 GB: 3-of-17   9.9 GB: 4-of-17   9.9 GB: 5-of-17   9.9 GB: 6-of-17   9.9 GB: 7-of-17   9.9 GB: 8-of-17   9.9 GB: 9-of-17   10.0 GB: 10-of-17   9.9 GB: 11-of-17   9.9 GB: 12-of-17   9.9 GB: 13-of-17   9.9 GB: 14-of-17   9.9 GB: 15-of-17   9.9 GB: 16-of-17   4.3 GB: 17-of-17
Supported Languagesfr it de es en
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Rank the Mixtral 8x7B Instruct V0.1 Upscaled 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