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

Deepseek Coder 6.7B 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 6.7B Instruct GPTQ Benchmarks

Rank the Deepseek Coder 6.7B 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 6.7B Instruct GPTQ (TheBloke/deepseek-coder-6.7B-instruct-GPTQ)

Best Alternatives to Deepseek Coder 6.7B Instruct GPTQ

Best Alternatives
HF Rank
...k Coder 6.7 Evol Feedback 4bit16K / 3.9 GB70
...oder 6.7B Instruct Hf 4bit Mlx16K / 4 GB50
...rpreter DS 6.7B 6.0bpw H6 EXL216K / 5.2 GB01
...rpreter DS 6.7B 8.0bpw H8 EXL216K / 6.9 GB01
Test16K / 0.3 GB270
...epseek Coder 6.7B Instruct AWQ16K / 3.9 GB94911
OpenCodeInterpreter DS 6.7B16K / 13.5 GB072
NaturalSQL 6.7B V016K / 13.5 GB1035
Speechless Coder Ds 6.7B16K / 13.5 GB19914
Code 290K 6.7B Instruct16K / 13.5 GB03

Deepseek Coder 6.7B Instruct GPTQ Parameters and Internals

LLM NameDeepseek Coder 6.7B Instruct GPTQ
RepositoryOpen on 🤗 
Model NameDeepseek Coder 6.7B Instruct
Model CreatorDeepSeek
Base Model(s)  Deepseek Coder 6.7B Instruct   deepseek-ai/deepseek-coder-6.7b-instruct
Model Size6.7b
Required VRAM3.9 GB
Model Typedeepseek
Model Files  3.9 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