LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Deepseek Coder 33B Instruct GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18870 in total.

  4-bit   Autotrain compatible Base model:deepseek-ai/deepsee...   Codegen   Conversational   Gptq   Instruct   License:other   Llama   Quantized   Region:us   Safetensors

Deepseek Coder 33B Instruct GPTQ Benchmarks

Rank the Deepseek Coder 33B Instruct 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  
Deepseek Coder 33B Instruct GPTQ (TheBloke/deepseek-coder-33B-instruct-GPTQ)

Best Alternatives to Deepseek Coder 33B Instruct GPTQ

Best Alternatives
HF Rank
...er 33B Instruct 3.0bpw H6 EXL216K / 13 GB21
...er 33B Instruct 4.0bpw H6 EXL216K / 17.1 GB34
...r 33B Instruct 4.65bpw H6 EXL216K / 19.8 GB50
...er 33B Instruct 5.0bpw H6 EXL216K / 21.2 GB90
...er 33B Instruct 6.0bpw H6 EXL216K / 25.4 GB50
...er 33B Instruct 8.0bpw H8 EXL216K / 33.6 GB22
...eepseek Coder 33B Instruct AWQ16K / 18.1 GB170529
Deepseek Coder 33B Instruct16K / 66.5 GB85293275

Deepseek Coder 33B Instruct GPTQ Parameters and Internals

LLM NameDeepseek Coder 33B Instruct GPTQ
RepositoryOpen on 🤗 
Model NameDeepseek Coder 33B Instruct
Model CreatorDeepSeek
Base Model(s)  Deepseek Coder 33B Instruct   deepseek-ai/deepseek-coder-33b-instruct
Model Size33b
Required VRAM17.4 GB
Model Typedeepseek
Model Files  17.4 GB
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<|begin▁of▁sentence|>
End of Sentence Token<|EOT|>
Vocabulary Size32256
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003