LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Starcoder2 7B by bigcode

 »  All LLMs  »  bigcode  »  Starcoder2 7B   URL Share it on

  60248   
  Arxiv:2004.05150   Arxiv:2205.14135   Arxiv:2207.14255   Arxiv:2305.13245   Arxiv:2402.19173   Autotrain compatible   Code Dataset:bigcode/the-stack-v2-t...   Endpoints compatible   Model-index   Region:us   Safetensors   Sharded   Starcoder2   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bigcode/starcoder2-7b 

Starcoder2 7B Benchmarks

MMLU Pro: 7.14
GPQA: 0.22
MUSR: 5.82
BBH: 11.4
IFEval: 22.09 vs 88 (so35)-74.9%
ARC: 38.31 vs 96.7 (so35)-60.4%
HellaSwag: 51.91 vs 95.3 (gpt4)-45.5%
MMLU: 41.21 vs 88.3 (so35)-53.3%
TruthfulQA: 41.99 vs 59 (gpt4)-28.8%
WinoGrande: 59.19 vs 87.5 (gpt4)-32.4%
GSM8K: 25.09 vs 96.4 (so35)-74%
HumanEvalA: 26.1
Python Eva: 34.09 vs 92 (so35)-62.9%
Java Eval: 29.42
Javascript: 35.35
CPP Eval: 33.63
PHP Eval: 30.58
Julia Eval: 20.42
D Eval: 15.12
Lua Eval: 30.67
R Eval: 16.72
Racket Eva: 11.58
Rust Eval: 29.62
Swift Eval: 26.06
MATH Lvl 5: 3.1
LLME Score: 0.30219
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starcoder2 7B (bigcode/starcoder2-7b)

Starcoder2 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
software development, educational tools
Primary Use Cases:
code generation, automated coding assistance
Limitations:
Not guaranteed to generate functioning code, Might contain inefficiencies or bugs
Additional Notes 
Model is not an instruction model and may not perform well with explicit commands like writing a square root computation.
Supported Languages 
EN (High), multi-language (Limited)
Training Details 
Data Sources:
GitHub code, Arxiv, Wikipedia
Data Volume:
3.5+ trillion tokens
Methodology:
Grouped Query Attention, a context window of 16,384 tokens, sliding window attention of 4,096 tokens, Fill-in-the-Middle objective
Hardware Used:
432 H100 GPUs
Model Architecture:
Transformer decoder with grouped-query and sliding window attention and Fill-in-the-Middle objective
Input Output 
Accepted Modalities:
text
LLM NameStarcoder2 7B
Repository 🤗https://huggingface.co/bigcode/starcoder2-7b 
Model Size7b
Required VRAM14.4 GB
Updated2025-04-22
Maintainerbigcode
Model Typestarcoder2
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureStarcoder2ForCausalLM
Licensebigcode-openrail-m
Context Length16384
Model Max Length16384
Transformers Version4.37.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typebfloat16
Activation Functiongelu

Quantized Models of the Starcoder2 7B

Model
Likes
Downloads
VRAM
Starcoder2 7B AWQ1104 GB
StarCoder2 7B GGUF1373252 GB

Best Alternatives to Starcoder2 7B

Best Alternatives
Context / RAM
Downloads
Likes
Dolphincoder Starcoder2 7B16K / 14.9 GB911
Starcoder2 7B Int4 Ov16K / 3.8 GB150
Jmg Starcoder2 7B 100K16K / 14.4 GB60
Starcoder2 7B Instruct16K / 14.4 GB1042
Speechless Starcoder2 7B16K / 14.4 GB45
OpenCodeInterpreter SC2 7B16K / 14.9 GB1014
Starcoder2 Chat16K / 28.8 GB322
...Starcoder2 7B Bnb 4bit Smashed16K / 4.4 GB50
Starcoder2 7B 4bit16K / 4.4 GB642
Starcoder2 7B AWQ16K / 4.5 GB101

Rank the Starcoder2 7B 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? 46565 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 v20241227
  Support LLM Explorer