Deepseek Coder 33B Instruct by deepseek-ai

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

  Autotrain compatible   Codegen   Conversational   Endpoints compatible   Instruct   License:other   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow

Deepseek Coder 33B Instruct Benchmarks

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  
Deepseek Coder 33B Instruct (deepseek-ai/deepseek-coder-33b-instruct)

Quantized Models of the Deepseek Coder 33B Instruct

...epseek Coder 33B Instruct GGUF152576514 GB
...eepseek Coder 33B Instruct AWQ32265818 GB
...epseek Coder 33B Instruct GPTQ2622774317 GB

Best Alternatives to Deepseek Coder 33B Instruct

Best Alternatives
HF Rank
Deepseek Wizard 33B Slerp16K / 35.3 GB17210
ValidateAI 3 33B Ties16K / 66.5 GB17210
ValidateAI 2 33B AT16K / 66.5 GB17210
NL2SQL DeepSeek 33B16K / 66.5 GB50
...epseek Coder 33B Instruct AQLM2K / 9.6 GB33 33B Instruct 3.0bpw H6 EXL216K / 13 GB31 33B Instruct 4.0bpw H6 EXL216K / 17.1 GB55
...r 33B Instruct 4.65bpw H6 EXL216K / 19.8 GB31 33B Instruct 5.0bpw H6 EXL216K / 21.2 GB11
...k Coder 33B Instruct 8bpw EXL216K / 31.9 GB130

Deepseek Coder 33B Instruct Parameters and Internals

LLM NameDeepseek Coder 33B Instruct
RepositoryOpen on 🤗 
Model Size33b
Required VRAM66.5 GB
Model Typellama
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
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
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 35130 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801