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

Yarn Mistral 7B 64K by NousResearch

 »  All LLMs  »  NousResearch  »  Yarn Mistral 7B 64K   URL Share it on

  10318   
  Arxiv:2309.00071   Autotrain compatible   Custom code Dataset:emozilla/yarn-train-to...   En   Endpoints compatible   Mistral   Pytorch   Region:us   Sharded   Yarn
Model Card on HF 🤗: https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k 

Yarn Mistral 7B 64K Benchmarks

MMLU Pro: 21.27
GPQA: 5.37
MUSR: 9.88
BBH: 20.23
IFEval: 20.8 vs 88 (so35)-76.4%
ARC: 59.9 vs 96.7 (so35)-38.1%
HellaSwag: 82.51 vs 95.3 (gpt4)-13.4%
MMLU: 62.96 vs 88.3 (so35)-28.7%
TruthfulQA: 41.86 vs 59 (gpt4)-29.1%
WinoGrande: 77.27 vs 87.5 (gpt4)-11.7%
GSM8K: 33.28 vs 96.4 (so35)-65.5%
MATH Lvl 5: 3.47
LLME Score: 0.24942
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yarn Mistral 7B 64K (NousResearch/Yarn-Mistral-7b-64k)

Yarn Mistral 7B 64K Parameters and Internals

Model Type 
language model
Additional Notes 
Further pretrained on long context data for 1000 steps.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
emoZilla/yarn-train-tokenized-16k-mistral
Methodology:
YaRN extension method
Context Length:
64000
Hardware Used:
JUWELS supercomputer
Model Architecture:
Language model architecture with support for extended context window.
LLM NameYarn Mistral 7B 64K
Repository 🤗https://huggingface.co/NousResearch/Yarn-Mistral-7b-64k 
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
MaintainerNousResearch
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Yarn Mistral 7B 64K

Model
Likes
Downloads
VRAM
Yarn Mistral 7B 64K GGUF322233 GB
...64K Instruct Alpaca Cleaned Q41237 GB
Yarn Mistral 7B 64K GPTQ4384 GB
Yarn Mistral 7B 64K AWQ4194 GB

Best Alternatives to Yarn Mistral 7B 64K

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
MegaBeam Mistral 7B 512K512K / 14.4 GB655449
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB647215
Hebrew Mistral 7B 200K256K / 30 GB489915
Astral 256K 7B V2250K / 14.4 GB60
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Yarn-Mistral-7b-64k.

Rank the Yarn Mistral 7B 64K 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