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

Deepseek Coder 6.7B Instruct by deepseek-ai

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

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

Deepseek Coder 6.7B Instruct Benchmarks

Rank the Deepseek Coder 6.7B 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 6.7B Instruct (deepseek-ai/deepseek-coder-6.7b-instruct)

Quantized Models of the Deepseek Coder 6.7B Instruct

...pseek Coder 6.7B Instruct GGUF1411382 GB
...pseek Coder 6.7B Instruct GPTQ2215053 GB
...epseek Coder 6.7B Instruct AWQ119493 GB
...k Coder 6.7 Evol Feedback 4bit073 GB

Best Alternatives to Deepseek Coder 6.7B Instruct

Best Alternatives
HF Rank
...eepseek Coder 7B Instruct V1.550.894K / 13.9 GB469550
CodeLlama 7B Instruct Onnx16K /  GB230
Small Codellama16K / 9.8 GB90
Codellama 7B Instruct Slerp16K / 13.4 GB60
CodeLlama 7B Instruct Hf16K / 13.5 GB58478162
MathCoder CL 7B16K / 13.5 GB3514
...Japanese CodeLlama 7B Instruct16K / 13.5 GB51913
...on Calling 6320 7B Instruct Hf16K / 13.5 GB58
StructLM 7B16K / 13.5 GB06
XAgentLlama 7B Preview16K / 13.5 GB95
Note: green Score (e.g. "73.2") means that the model is better than deepseek-ai/deepseek-coder-6.7b-instruct.

Deepseek Coder 6.7B Instruct Parameters and Internals

LLM NameDeepseek Coder 6.7B Instruct
RepositoryOpen on 🤗 
Model Size7b
Required VRAM13.5 GB
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
Context Length16384
Model Max Length16384
Transformers Version4.34.1
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