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

Mistral RAG by DeepMount00

 »  All LLMs  »  DeepMount00  »  Mistral RAG   URL Share it on

  1809   
  Autotrain compatible   Dataset:deepmount00/gquad it   Endpoints compatible   It   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Mistral RAG Benchmarks

ARC: 52.9 vs 96.7 (so35)-45.3%
HellaSwag: 81.58 vs 95.3 (gpt4)-14.4%
MMLU: 23.12 vs 88.3 (so35)-73.8%
TruthfulQA: 62.48 vs 59 (gpt4)5.9%
WinoGrande: 73.88 vs 87.5 (gpt4)-15.6%
GSM8K: 52.84 vs 96.4 (so35)-45.2%
LLME Score: 0.27542
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Mistral RAG Parameters and Internals

LLM NameMistral RAG
Repository 🤗https://huggingface.co/DeepMount00/Mistral-RAG 
Model Size7.2b
Required VRAM14.4 GB
Updated2024-09-07
MaintainerDeepMount00
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16
Mistral RAG (DeepMount00/Mistral-RAG)

Best Alternatives to Mistral RAG

Best Alternatives
Context / RAM
Downloads
Likes
Spydaz Web AI 08512K / 14.5 GB661
Spydaz Web AI ChatQA 001 SFT512K / 14.4 GB01
Spydaz Web AI ChatQA 001 UFT512K / 14.4 GB01
Spydaz Web AI ChatML 002512K / 14.4 GB190
Spydaz Web AI ChatQA 001512K / 14.4 GB70
Openchat 3.5 0106 128K DPO128K / 14.4 GB582
Mistral7B PairRM SPPO Iter232K / 14.4 GB48281
Mistral7B PairRM SPPO Iter332K / 14.4 GB49405
GutenLaserPi32K / 14.5 GB190
WestlakeMaziyar 7B Slerp32K / 14.5 GB320
Note: green Score (e.g. "73.2") means that the model is better than DeepMount00/Mistral-RAG.

Rank the Mistral RAG 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? 35693 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 v2024072803
  Support LLM Explorer