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

Saily 220B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Saily 220B GPTQ   URL Share it on

  10   
  4-bit   Autotrain compatible Base model:deepnight-research/... Base model:quantized:deepnight...   Dataset:eleutherai/pile   Dataset:meta-math/metamathqa Dataset:tiiuae/falcon-refinedw...   En   Gptq   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Saily_220B-GPTQ 

Saily 220B GPTQ Benchmarks

LLME Score: 0.13739
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 🚀

Saily 220B GPTQ Parameters and Internals

Model Type 
llama
Additional Notes 
Limitations include the possibility of incorrect or biased content generation.
Supported Languages 
English (primary)
Training Details 
Data Sources:
tiiuae/falcon-refinedweb, EleutherAI/pile, meta-math/MetaMathQA, Unnatural Code
Methodology:
Built on top of Llama2-70B merges, 10 fine-tuned models; multiple merges created keeping Logical-Understanding and Reasoning models constant.
Hardware Used:
4 x A100 80GB GPUs, 2 x A100 80GB GPUs
Model Architecture:
Llama2-70B fine-tuned models with multiple merges.
Input Output 
Input Format:
Use the Alpaca Prompt Format with Instruction and Response tags.
Output Format:
Textual response output following given instruction.
Performance Tips:
Load in 4bit or 8bit for optimization; please use INSTRUCT or CHAT-INSTRUCT mode in Text-Generation-WebUI.
Release Notes 
Version:
v1
Date:
17th December, 2023
Notes:
Released as a powerful model built on Llama2-70B merges; 10 models fine-tuned on specific domains; uses public datasets and internal transcriptions.
LLM NameSaily 220B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Saily_220B-GPTQ 
Model NameSaily 220B
Model CreatorDEEPNIGHT
Base Model(s)  Saily 220B   deepnight-research/Saily_220B
Model Size220b
Required VRAM105.2 GB
Updated2025-06-09
MaintainerTheBloke
Model Typellama
Model Files  49.0 GB: 1-of-3   48.9 GB: 2-of-3   7.3 GB: 3-of-3
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16
Saily 220B GPTQ (TheBloke/Saily_220B-GPTQ)

Best Alternatives to Saily 220B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...l Llama 220M GQA 32K Theta Sft32K / 0.4 GB172
Smol Llama 220M GQA 32K Theta32K / 0.4 GB151
Saily 220B4K / 417 GB28120
Saily 220B AWQ4K / 109.1 GB130
Smol Llama 220M GQA2K / 0.4 GB77112
Smol Llama 220M Openhermes2K / 0.4 GB1955
...mol Llama 220M GQA Fineweb Edu2K / 0.4 GB201
Smol Llama 220M Open Instruct2K / 0.4 GB222
Smol Llama 220M Bees Internal2K / 0.4 GB211
Beecoder 220M Python2K / 0.4 GB222
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Saily_220B-GPTQ.

Rank the Saily 220B GPTQ 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? 48046 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