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 6.7B Base by deepseek-ai

 »  All LLMs  »  deepseek-ai  »  Deepseek Coder 6.7B Base   URL Share it on

  154536   
  Autotrain compatible   Codegen   Endpoints compatible   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base 

Deepseek Coder 6.7B Base Benchmarks

ARC: 37.03 vs 96.7 (so35)-61.7%
HellaSwag: 53.46 vs 95.3 (gpt4)-43.9%
MMLU: 38.39 vs 88.3 (so35)-56.5%
TruthfulQA: 40.28 vs 59 (gpt4)-31.7%
WinoGrande: 58.09 vs 87.5 (gpt4)-33.6%
GSM8K: 17.97 vs 96.4 (so35)-81.4%
HumanEvalA: 33.54
Python Eva: 45.83 vs 92 (so35)-50.2%
Java Eval: 37.72
Javascript: 45.9
CPP Eval: 45.53
PHP Eval: 36.92
Julia Eval: 28.74
D Eval: 19.74
Lua Eval: 33.89
R Eval: 28.99
Racket Eva: 18.73
Rust Eval: 34.67
Swift Eval: 25.8
LLME Score: 0.23685
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Coder 6.7B Base (deepseek-ai/deepseek-coder-6.7b-base)
🌟 Advertise your project 🚀

Deepseek Coder 6.7B Base Parameters and Internals

Model Type 
code completion, code insertion, repository level code completion
Use Cases 
Areas:
code development, software engineering
Primary Use Cases:
project-level code completion, code infilling
Additional Notes 
Offers various sizes from 1.3B to 33B parameters.
Supported Languages 
English (code and natural language), Chinese (code and natural language)
Training Details 
Data Sources:
code, natural language
Data Volume:
2 trillion tokens
Context Length:
16000
Model Architecture:
Multi-Head Attention
LLM NameDeepseek Coder 6.7B Base
Repository 🤗https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base 
Model Size6.7b
Required VRAM13.5 GB
Updated2025-09-23
Maintainerdeepseek-ai
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2   10.0 GB: 1-of-2   3.5 GB: 2-of-2
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size32256
Torch Data Typebfloat16

Quantized Models of the Deepseek Coder 6.7B Base

Model
Likes
Downloads
VRAM
Deepseek Coder 6.7B Base GGUF1629442 GB
Deepseek Coder 6.7B Base AWQ10713 GB
Deepseek Coder 6.7B Base GPTQ5133 GB
Deepseek Coder 6.7B Base AWQ003 GB

Best Alternatives to Deepseek Coder 6.7B Base

Best Alternatives
Context / RAM
Downloads
Likes
Speechless Coder Ds 6.7B16K / 13.5 GB18887
...s Coder6.7b Reflct Adamw Iter116K / 13.5 GB4750
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB950
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB1100
...r6.7b Pos Reflct Rmsprop Iter116K / 13.5 GB870
...ir4 Ds Coder6.7b Rmsprop Iter116K / 13.5 GB430
...r6.7b Pos Reflct Rmsprop Iter116K / 13.5 GB900
...Coder6.7b Reflct Rmsprop Iter116K / 13.5 GB620
Ds Coder6.7b Rmsprop Iter116K / 13.5 GB670
Semcoder S 103016K / 13.5 GB453

Rank the Deepseek Coder 6.7B Base 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? 51544 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 v20241124
  Support LLM Explorer