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

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Everyone Coder 33B V2 Base 8.0bpw H8 EXL2   URL Share it on

  7   

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 is an open-source language model by LoneStriker. Features: 33b LLM, VRAM: 33.5GB, Context: 16K, License: other, Quantized, Code Generating, LLM Explorer Score: 0.12.

  Autotrain compatible   Codegen   Endpoints compatible   Exl2   Llama   Merge   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2 

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 Benchmarks

LLME Score: 0.11829
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 (LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2)
🌟 Advertise your project 🚀

Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
coding-specific
Additional Notes 
This Version 2 of the Everything-Coder-33b model uses the task_arithmetic merging method which significantly enhances coding performance. It addresses previous merging issues while maintaining model integrity.
Training Details 
Data Sources:
deepseek-ai/deepseek-coder-33b-instruct, codefuse-ai/CodeFuse-DeepSeek-33B, WizardLM/WizardCoder-33B-V1.1
Methodology:
fine-tuning and task_arithmetic merging
Input Output 
Input Format:
Alpaca prompt format
LLM NameEveryone Coder 33B V2 Base 8.0bpw H8 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2 
Model Size33b
Required VRAM33.5 GB
Updated2025-09-23
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-4   8.5 GB: 2-of-4   8.5 GB: 3-of-4   7.9 GB: 4-of-4
Quantization Typeexl2
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size32256
Torch Data Typefloat16

Best Alternatives to Everyone Coder 33B V2 Base 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...erpreter DS 33B 4.0bpw H6 EXL216K / 17.1 GB34
...rpreter DS 33B 4.65bpw H6 EXL216K / 19.8 GB13
...erpreter DS 33B 6.0bpw H6 EXL216K / 25.3 GB71
...erpreter DS 33B 5.0bpw H6 EXL216K / 21.2 GB11
...erpreter DS 33B 8.0bpw H8 EXL216K / 33.5 GB01
...Coder 33B Base 4.65bpw H6 EXL216K / 19.8 GB51
... Coder 33B Base 6.0bpw H6 EXL216K / 25.3 GB41
...abbitNeo 33B V1.4.0bpw H6 EXL216K / 17.1 GB11
...er 33B Instruct 4.0bpw H6 EXL216K / 17.1 GB35
...er 33B Instruct 8.0bpw H8 EXL216K / 33.6 GB13
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Everyone-Coder-33b-v2-Base-8.0bpw-h8-exl2.

Rank the Everyone Coder 33B V2 Base 8.0bpw H8 EXL2 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? 52721 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