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

Deepseek Coder 33B Instruct by deepseek-ai

 »  All LLMs  »  deepseek-ai  »  Deepseek Coder 33B Instruct   URL Share it on

  33468   
  Autotrain compatible   Codegen   Conversational   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct 

Deepseek Coder 33B Instruct Benchmarks

HumanEvalA: 49.99
Python Eva: 80.02 vs 92 (so35)-13%
Java Eval: 52.03
Javascript: 65.13
CPP Eval: 62.36
PHP Eval: 52.5
Julia Eval: 42.92
D Eval: 17.85
Lua Eval: 50.92
R Eval: 39.43
Racket Eva: 31.69
Rust Eval: 55.56
Swift Eval: 49.42
LLME Score: 0.22733
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Coder 33B Instruct (deepseek-ai/deepseek-coder-33b-instruct)

Deepseek Coder 33B Instruct Parameters and Internals

Model Type 
code generation, text generation
Use Cases 
Areas:
coding, software development, research
Applications:
code completion, programming assistance, educational tools
Primary Use Cases:
Project-level code completion, Infilling tasks
Supported Languages 
English (high), Chinese (high)
Training Details 
Data Sources:
Project-level code corpus
Data Volume:
2T tokens
Methodology:
Pre-trained with a window size of 16K and an extra fill-in-the-blank task
Context Length:
16000
LLM NameDeepseek Coder 33B Instruct
Repository 🤗https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct 
Model Size33b
Required VRAM66.5 GB
Updated2025-03-12
Maintainerdeepseek-ai
Model Typellama
Instruction-BasedYes
Model Files  9.7 GB: 1-of-7   9.9 GB: 2-of-7   9.9 GB: 3-of-7   9.8 GB: 4-of-7   9.9 GB: 5-of-7   9.9 GB: 6-of-7   7.4 GB: 7-of-7   9.7 GB: 1-of-7   9.9 GB: 2-of-7   9.9 GB: 3-of-7   9.8 GB: 4-of-7   9.9 GB: 5-of-7   9.9 GB: 6-of-7   7.4 GB: 7-of-7
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<|EOT|>
Vocabulary Size32256
Torch Data Typebfloat16

Quantized Models of the Deepseek Coder 33B Instruct

Model
Likes
Downloads
VRAM
...epseek Coder 33B Instruct GGUF1672424514 GB
...eepseek Coder 33B Instruct AWQ36273818 GB
...epseek Coder 33B Instruct GPTQ2643717 GB

Best Alternatives to Deepseek Coder 33B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Wizard 33B Slerp16K / 35.3 GB90
ValidateAI 3 33B Ties16K / 66.5 GB70
ValidateAI 2 33B AT16K / 66.5 GB100
...epseek Coder 33B Instruct AQLM2K / 9.6 GB183
...er 33B Instruct 4.0bpw H6 EXL216K / 17.1 GB135
...er 33B Instruct 8.0bpw H8 EXL216K / 33.6 GB133
...er 33B Instruct 3.0bpw H6 EXL216K / 13 GB161
...r 33B Instruct 4.65bpw H6 EXL216K / 19.8 GB141
...er 33B Instruct 5.0bpw H6 EXL216K / 21.2 GB121
...eepseek Coder 33B Instruct AWQ16K / 18.1 GB273836

Rank the Deepseek Coder 33B Instruct 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? 44887 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 v20241227
  Support LLM Explorer