Saily 220B AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Saily 220B AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:deepnight-research/... Base model:quantized:deepnight...   Dataset:eleutherai/pile   Dataset:meta-math/metamathqa Dataset:tiiuae/falcon-refinedw...   En   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/TheBloke/Saily_220B-AWQ 

Saily 220B AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Saily 220B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Limitations:
Saily 220B may generate incorrect or biased content.
Additional Notes 
Please don't refer to the config.json in the files, it isn't accurate.
Supported Languages 
en (English)
Training Details 
Data Sources:
tiiuae/falcon-refinedweb, EleutherAI/pile, meta-math/MetaMathQA, Unnatural Code (Javascript, Python, C++)
Hardware Used:
4 x A100 80GB, 2 x A100 80GB
Model Architecture:
Llama2-70B merges
Input Output 
Input Format:
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
v1
Date:
17th December, 2023
Notes:
Releasing Saily_220B, built on top of Llama2-70B merges with various fine-tuning datasets.
LLM NameSaily 220B AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Saily_220B-AWQ 
Model NameSaily 220B
Model CreatorDEEPNIGHT
Base Model(s)  Saily 220B   deepnight-research/Saily_220B
Model Size220b
Required VRAM109.1 GB
Updated2025-06-10
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-11   9.9 GB: 2-of-11   9.9 GB: 3-of-11   10.0 GB: 4-of-11   9.9 GB: 5-of-11   9.9 GB: 6-of-11   10.0 GB: 7-of-11   9.9 GB: 8-of-11   9.9 GB: 9-of-11   10.0 GB: 10-of-11   9.8 GB: 11-of-11
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16
Saily 220B AWQ (TheBloke/Saily_220B-AWQ)

Best Alternatives to Saily 220B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...l Llama 220M GQA 32K Theta Sft32K / 0.4 GB182
Smol Llama 220M GQA 32K Theta32K / 0.4 GB161
Saily 220B4K / 417 GB34420
Saily 220B GPTQ4K / 105.2 GB241
Smol Llama 220M GQA2K / 0.4 GB91812
Smol Llama 220M Openhermes2K / 0.4 GB2415
...mol Llama 220M GQA Fineweb Edu2K / 0.4 GB211
Smol Llama 220M Open Instruct2K / 0.4 GB232
Smol Llama 220M Bees Internal2K / 0.4 GB261
Beecoder 220M Python2K / 0.4 GB232
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Saily_220B-AWQ.

Rank the Saily 220B AWQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 48075 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124