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

SaiLy Experiment V1 by deepnight-research

 »  All LLMs  »  deepnight-research  »  SaiLy Experiment V1   URL Share it on

  13   

SaiLy Experiment V1 is an open-source language model by deepnight-research. Features: 69b LLM, VRAM: 276GB, Context: 4K, License: other, LLM Explorer Score: 0.1.

  Conversational   Deepnight   Deepnight-research   En   Endpoints compatible   Experiment   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepnight-research/SaiLy_experiment_v1 

SaiLy Experiment V1 Benchmarks

LLME Score: 0.10201
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SaiLy Experiment V1 (deepnight-research/SaiLy_experiment_v1)
🌟 Advertise your project 🚀

SaiLy Experiment V1 Parameters and Internals

Model Type 
conversational
Additional Notes 
This is an experimental model. We built this, but the model's functionalities are uncertain.
Supported Languages 
en (unknown)
Training Details 
Methodology:
Random things.
Context Length:
8000
Input Output 
Performance Tips:
Model can use up to 5k context perfectly without any precision loss. Majority of the loss in precision and contextual relation establishment is between 5k to 7k.
LLM NameSaiLy Experiment V1
Repository 🤗https://huggingface.co/deepnight-research/SaiLy_experiment_v1 
Model Size69b
Required VRAM276 GB
Updated2026-05-22
Maintainerdeepnight-research
Model Typellama
Model Files  19.7 GB: 1-of-15   19.9 GB: 2-of-15   19.6 GB: 3-of-15   19.3 GB: 4-of-15   19.3 GB: 5-of-15   19.6 GB: 6-of-15   20.0 GB: 7-of-15   19.6 GB: 8-of-15   19.6 GB: 9-of-15   19.6 GB: 10-of-15   20.0 GB: 11-of-15   19.6 GB: 12-of-15   19.6 GB: 13-of-15   19.1 GB: 14-of-15   1.5 GB: 15-of-15
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to SaiLy Experiment V1

Best Alternatives
Context / RAM
Downloads
Likes
...ine Tu Ophtho 3 1e 05 Stanford4K / 138.7 GB50
StableBeluga24K / 1.7 GB2205720
V Alpha Tross4K / 138.7 GB13520
Uni TianYan V14K / 138 GB2480
Airoboros L2 C70b 3.1.24K / 138 GB2310
Model 007 Preview4K / 138 GB9171
QCammel 70 X AWQ4K / 36.6 GB151
QCammel 70 X GPTQ4K / 35.3 GB272
Note: green Score (e.g. "73.2") means that the model is better than deepnight-research/SaiLy_experiment_v1.

Rank the SaiLy Experiment V1 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? 53972 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer