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 1.3B Instruct GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Deepseek Coder 1.3B Instruct GPTQ   URL Share it on

  906   
  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-1.3b-instruct-GPTQ 

Deepseek Coder 1.3B Instruct GPTQ Benchmarks

LLME Score: 0.12735
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Coder 1.3B Instruct GPTQ (TheBloke/deepseek-coder-1.3b-instruct-GPTQ)
🌟 Advertise your project 🚀

Deepseek Coder 1.3B Instruct GPTQ Parameters and Internals

Model Type 
deepseek, code language model
Use Cases 
Areas:
code completion, instruction following
Applications:
HumanEval, MultiPL-E, MBPP, DS-1000, APPS benchmarks
Supported Languages 
English (both code and natural language (87% code, 13% natural language)), Chinese (both code and natural language (87% code, 13% natural language))
Training Details 
Data Sources:
2T tokens including code and linguistic data
Data Volume:
2T tokens
Methodology:
Trained from scratch with a window size of 16K and additional fill-in-the-blank task
Context Length:
16000
Input Output 
Input Format:
{prompt}
LLM NameDeepseek Coder 1.3B Instruct GPTQ
Repository 🤗https://huggingface.co/TheBloke/deepseek-coder-1.3b-instruct-GPTQ 
Model NameDeepseek Coder 1.3B Instruct
Model CreatorDeepSeek
Base Model(s)  deepseek-ai/deepseek-coder-1.3b-instruct   deepseek-ai/deepseek-coder-1.3b-instruct
Model Size1.3b
Required VRAM0.9 GB
Updated2025-10-02
MaintainerTheBloke
Model Typedeepseek
Instruction-BasedYes
Model Files  0.9 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 1.3B Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Coder 1.3B Instruct16K / 2.7 GB363955138
Speechless Coder Ds 1.3B16K / 2.7 GB17760
...c Deepseek Coder 1.3B Instruct16K / 5.4 GB50
Hpc Coder V2.1.3B16K / 2.7 GB74
... 1.3B Instruct Trt Int4 G64 Hf16K / 0.9 GB130
...t Structured Output Peft Merge16K / 2.7 GB60
Datascience Coder 1.3B16K / 2.7 GB51
...epseek Coder 1.3B Instruct AWQ8K / 0.9 GB153
...Coder 1.3B Function Calling V116K / 2.7 GB2022
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-1.3b-instruct-GPTQ.

Rank the Deepseek Coder 1.3B 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? 51552 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