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

Quietstar 8 Ahead by ezelikman

 »  All LLMs  »  ezelikman  »  Quietstar 8 Ahead   URL Share it on

  125   
  Arxiv:2403.09629   Autotrain compatible Dataset:open-web-math/open-web...   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ezelikman/quietstar-8-ahead 

Quietstar 8 Ahead Benchmarks

LLME Score: 0.15446
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Quietstar 8 Ahead (ezelikman/quietstar-8-ahead)
🌟 Advertise your project 🚀

Quietstar 8 Ahead Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
open-web-math/open-web-math
Methodology:
continued pretraining using Quiet-STaR for generating 8 thought tokens before each output token.
LLM NameQuietstar 8 Ahead
Repository 🤗https://huggingface.co/ezelikman/quietstar-8-ahead 
Model Size7.3b
Required VRAM14.5 GB
Updated2025-10-07
Maintainerezelikman
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.6 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Quietstar 8 Ahead

Best Alternatives
Context / RAM
Downloads
Likes
Dictalm2.0 Instruct32K / 14.5 GB20062924
Dictalm2.032K / 14.5 GB614424
My Tokenizer 50 2000032K / 14.6 GB50
My Tokenizer 100 1000032K / 22.3 GB50
... Fine Tuned Alpaca Gpt4 Hebrew32K / 14.5 GB49410
Dictalm2.0 Instruct Fine Tuned32K / 14.5 GB47240
Mis32K / 14.6 GB60
Dictalm2 It Qa Fine Tune32K / 14.5 GB13527
Misjava Api 060924 V3 Merged32K / 14.6 GB70
Swallow Hermes St V14K / 14.6 GB314
Note: green Score (e.g. "73.2") means that the model is better than ezelikman/quietstar-8-ahead.

Rank the Quietstar 8 Ahead 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? 51544 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 v20241124
  Support LLM Explorer