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

Stealth Rag V1.1 by jan-hq

 »  All LLMs  »  jan-hq  »  Stealth Rag V1.1   URL Share it on

  18   
  Alignment-handbook   Autotrain compatible Base model:finetune:tinyllama/... Base model:tinyllama/tinyllama...   Conversational Dataset:jan-hq/bagel sft binar... Dataset:jan-hq/dolphin binariz... Dataset:jan-hq/openhermes bina...   Endpoints compatible   Generated from trainer   Mistral   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/jan-hq/stealth-rag-v1.1 

Stealth Rag V1.1 Benchmarks

ARC: 62.12 vs 96.7 (so35)-35.8%
HellaSwag: 83.83 vs 95.3 (gpt4)-12%
MMLU: 64.06 vs 88.3 (so35)-27.5%
TruthfulQA: 49.64 vs 59 (gpt4)-15.9%
WinoGrande: 79.32 vs 87.5 (gpt4)-9.3%
GSM8K: 67.78 vs 96.4 (so35)-29.7%
LLME Score: 0.16005
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Stealth Rag V1.1 Parameters and Internals

LLM NameStealth Rag V1.1
Repository 🤗https://huggingface.co/jan-hq/stealth-rag-v1.1 
Base Model(s)  TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T   TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
Model Size1.1b
Required VRAM14.4 GB
Updated2025-06-09
Maintainerjan-hq
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16
Stealth Rag V1.1 (jan-hq/stealth-rag-v1.1)

Best Alternatives to Stealth Rag V1.1

Best Alternatives
Context / RAM
Downloads
Likes
Hare 1.1B Base 0.5v32K / 2.4 GB470
TinyLlama Mistral32K / 4.4 GB112
Mistral 1.1B Testing32K / 4.4 GB36101
Hare 1.1B Base32K / 2.2 GB817
Hare 1.1B Chat32K / 2.2 GB370
Dipsmol32K / 2.2 GB90
Hare 1.1B Tool32K / 2.2 GB101
Stealth Rag V1 E132K / 14.4 GB181
Mallam 1.1B 409632K / 2.2 GB4598
... Mistral 1.1B Databricks Dolly4K / 2.4 GB541
Note: green Score (e.g. "73.2") means that the model is better than jan-hq/stealth-rag-v1.1.

Rank the Stealth Rag V1.1 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? 48023 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