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 Base GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Deepseek Coder 33B Base GPTQ   URL Share it on

  43   
  4-bit   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Codegen   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-33B-base-GPTQ 

Deepseek Coder 33B Base GPTQ Benchmarks

LLME Score: 0.14457
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 Base GPTQ (TheBloke/deepseek-coder-33B-base-GPTQ)

Deepseek Coder 33B Base GPTQ Parameters and Internals

Model Type 
deepseek, code language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
HumanEval, MultiPL-E, MBPP, DS-1000, APPS benchmarks
Primary Use Cases:
Code completion, Infilling
Additional Notes 
Generates state-of-the-art performance among open-source code models.
Supported Languages 
primary_language (English), other_languages (Chinese), proficiency_level ()
Training Details 
Data Sources:
2T tokens, 87% code, 13% English and Chinese language data
Data Volume:
2 trillion tokens
Methodology:
Grouped-Query Attention, window size 16K, fill-in-the-blank task
Context Length:
16000
Model Architecture:
Grouped-Query Attention
Input Output 
Input Format:
{prompt}
Accepted Modalities:
text
LLM NameDeepseek Coder 33B Base GPTQ
Repository 🤗https://huggingface.co/TheBloke/deepseek-coder-33B-base-GPTQ 
Model NameDeepseek Coder 33B Base
Model CreatorDeepSeek
Base Model(s)  Deepseek Coder 33B Base   deepseek-ai/deepseek-coder-33b-base
Model Size33b
Required VRAM17.4 GB
Updated2025-02-05
MaintainerTheBloke
Model Typedeepseek
Model Files  17.4 GB
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size32256
Torch Data Typebfloat16

Best Alternatives to Deepseek Coder 33B Base GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Everyone Coder 33B Base GPTQ16K / 17.4 GB183
CodeFuse DeepSeek 33B 4bits16K / 18.7 GB2510
...epseek Coder 33B Instruct GPTQ16K / 17.4 GB23026
Vicuna 33B Coder GPTQ2K / 16.9 GB181
...erpreter DS 33B 4.0bpw H6 EXL216K / 17.1 GB54
...erpreter DS 33B 8.0bpw H8 EXL216K / 33.5 GB52
...rpreter DS 33B 4.65bpw H6 EXL216K / 19.8 GB42
...erpreter DS 33B 5.0bpw H6 EXL216K / 21.2 GB51
...erpreter DS 33B 6.0bpw H6 EXL216K / 25.3 GB51
...der 33B V2 Base 8.0bpw H8 EXL216K / 33.5 GB31
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-33B-base-GPTQ.

Rank the Deepseek Coder 33B Base 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? 42625 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