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 AWQ by TheBloke

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

  27   
  4-bit   Autotrain compatible   Awq Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Codegen   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Deepseek Coder 33B Base AWQ Benchmarks

LLME Score: 0.15697
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 AWQ Parameters and Internals

Model Type
deepseek
Use Cases
Areas:
Research, Commercial applications
Applications:
Project-level code completion, Code infilling
Primary Use Cases:
Coding capabilities for multiple programming languages
Supported Languages
English (fluent), Chinese (fluent)
Training Details
Data Sources:
Project-level code corpus with a mix of 87% code and 13% natural language in English and Chinese
Data Volume:2 trillion tokens
Methodology:Grouped-Query Attention with additional fill-in-the-blank task for supporting project-level code completion and infilling
Context Length:16384
Hardware Used:
Provided by Massed Compute
Model Architecture:Grouped-Query Attention
Input Output
Input Format:{prompt}
Accepted Modalities:
text
Output Format:Generated text/code
LLM NameDeepseek Coder 33B Base AWQ
Repository 🤗https://huggingface.co/TheBloke/deepseek-coder-33B-base-AWQ 
Model NameDeepseek Coder 33B Base
Model CreatorDeepSeek
Base Model(s)  Deepseek Coder 33B Base   deepseek-ai/deepseek-coder-33b-base
Model Size33b
Required VRAM18.1 GB
Updated2024-11-12
MaintainerTheBloke
Model Typedeepseek
Model Files  10.0 GB: 1-of-2   8.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
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 Typefloat16
Deepseek Coder 33B Base AWQ (TheBloke/deepseek-coder-33B-base-AWQ)

Best Alternatives to Deepseek Coder 33B Base AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...eepseek Coder 33B Instruct AWQ16K / 18.1 GB8476734
Everyone Coder 33B Base AWQ16K / 18.1 GB122
Vicuna 33B Coder AWQ2K / 17.6 GB111
...erpreter DS 33B 5.0bpw H6 EXL216K / 21.2 GB1081
...erpreter DS 33B 4.0bpw H6 EXL216K / 17.1 GB134
...rpreter DS 33B 4.65bpw H6 EXL216K / 19.8 GB142
...erpreter DS 33B 8.0bpw H8 EXL216K / 33.5 GB122
...erpreter DS 33B 6.0bpw H6 EXL216K / 25.3 GB121
...der 33B V2 Base 8.0bpw H8 EXL216K / 33.5 GB81
...Coder 33B Base 4.65bpw H6 EXL216K / 19.8 GB21
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-33B-base-AWQ.

Rank the Deepseek Coder 33B Base AWQ 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? 37901 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 v20241110
  Support LLM Explorer