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 Instruct GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Deepseek Coder 6.7B Instruct GPTQ   URL Share it on

  162   
  4-bit   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Codegen   Conversational   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GPTQ 

Deepseek Coder 6.7B Instruct GPTQ Benchmarks

LLME Score: 0.1579
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 Instruct GPTQ (TheBloke/deepseek-coder-6.7B-instruct-GPTQ)

Deepseek Coder 6.7B Instruct GPTQ Parameters and Internals

Model Type 
code generation, instruction-following
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
project-level code completion, infilling tasks
Supported Languages 
English (high), Chinese (high)
Training Details 
Data Sources:
87% code, 13% linguistic data in both English and Chinese
Data Volume:
2T tokens
Methodology:
Trained from scratch with fine-tuning on instruction data
Context Length:
16000
Model Architecture:
Code language model with a fill-in-the-blank task.
Input Output 
Input Format:
Chat format
Accepted Modalities:
text
Output Format:
Text
LLM NameDeepseek Coder 6.7B Instruct GPTQ
Repository 🤗https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct-GPTQ 
Model NameDeepseek Coder 6.7B Instruct
Model CreatorDeepSeek
Base Model(s)  deepseek-ai/deepseek-coder-6.7b-instruct   deepseek-ai/deepseek-coder-6.7b-instruct
Model Size6.7b
Required VRAM3.9 GB
Updated2024-12-22
MaintainerTheBloke
Model Typedeepseek
Instruction-BasedYes
Model Files  3.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
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
Torch Data Typebfloat16

Best Alternatives to Deepseek Coder 6.7B Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...rpreter DS 6.7B 6.0bpw H6 EXL216K / 5.2 GB62
...rpreter DS 6.7B 8.0bpw H8 EXL216K / 6.9 GB42
...rpreter DS 6.7B 4.0bpw H6 EXL216K / 3.6 GB51
...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
...r6.7b Pos Reflct Rmsprop Iter116K / 13.5 GB900
...ir4 Ds Coder6.7b Rmsprop Iter116K / 13.5 GB430
Ds Coder6.7b Rmsprop Iter116K / 13.5 GB670
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-6.7B-instruct-GPTQ.

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  

What open-source LLMs or SLMs are you in search of? 40066 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 v20241217
  Support LLM Explorer