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

Starcoder2 7B AWQ by TechxGenus

 »  All LLMs  »  TechxGenus  »  Starcoder2 7B AWQ   URL Share it on

  18   

Starcoder2 7B AWQ is an open-source language model by TechxGenus. Features: 7b LLM, VRAM: 4.5GB, Context: 16K, License: bigcode-openrail-m, Quantized, HF Score: 43, LLM Explorer Score: 0.16, Arc: 38.3, HellaSwag: 51.9, MMLU: 41.2, TruthfulQA: 42, WinoGrande: 59.2, GSM8K: 25.1, HumanEval: 34.1.

  Arxiv:2004.05150   Arxiv:2205.14135   Arxiv:2207.14255   Arxiv:2305.13245   4-bit   Awq   Code Dataset:bigcode/the-stack-v2-t...   Endpoints compatible   Model-index   Quantized   Region:us   Safetensors   Starcoder2
Model Card on HF 🤗: https://huggingface.co/TechxGenus/starcoder2-7b-AWQ 

Starcoder2 7B AWQ Benchmarks

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
LLME Score: 0.1648
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starcoder2 7B AWQ (TechxGenus/starcoder2-7b-AWQ)
🌟 Advertise your project 🚀

Starcoder2 7B AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Code generation tasks
Applications:
Text generation for programming based tasks
Primary Use Cases:
Generating code snippets, Preliminary code suggestions
Limitations:
Generated code may be inefficient or contain bugs., It is not an instruction model, so specific prompts like 'Write a function that computes the square root.' may not work well.
Considerations:
The model should be used considering it might produce output that requires human validation due to possible bugs or inefficiencies.
Additional Notes 
Consider the ethical and attribution aspects when using outputs from this model.
Supported Languages 
programming_languages_supported ( The model was trained on 17 programming languages from The Stack v2)
Training Details 
Data Sources:
GitHub code, Arxiv, Wikipedia
Data Volume:
3.5+ trillion tokens
Methodology:
The model uses Grouped Query Attention and a Fill-in-the-Middle objective with a sliding window attention
Context Length:
16384
Hardware Used:
432 H100 GPUs
Model Architecture:
Transformer decoder with grouped-query and sliding window attention
Input Output 
Input Format:
Programming code prompts.
Accepted Modalities:
text
Output Format:
Generated text/code snippets
Performance Tips:
Use context-rich prompts for better quality responses.
LLM NameStarcoder2 7B AWQ
Repository 🤗https://huggingface.co/TechxGenus/starcoder2-7b-AWQ 
Base Model(s)  Starcoder2 7B   bigcode/starcoder2-7b
Model Size7b
Required VRAM4.5 GB
Updated2026-04-10
MaintainerTechxGenus
Model Typestarcoder2
Model Files  4.5 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureStarcoder2ForCausalLM
Licensebigcode-openrail-m
Context Length16384
Model Max Length16384
Transformers Version4.39.3
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typefloat16
Activation Functiongelu

Best Alternatives to Starcoder2 7B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...Starcoder2 7B Bnb 4bit Smashed16K / 4.4 GB60
Starcoder2 7B 4bit16K / 4.4 GB2502
Starcoder2 7B16K / 14.4 GB45102190
Dolphincoder Starcoder2 7B16K / 14.9 GB711
StarCoder2 7B GGUF16K / 2.7 GB205318
Starcoder2 7B Int4 Ov16K / 3.8 GB150
Jmg Starcoder2 7B 100K16K / 14.4 GB50
Starcoder2 7B Instruct GPTQ16K / 4.5 GB32
Starcoder2 7B GPTQ16K / 4.5 GB82
Dolphincoder Starcoder2 7B16K / 14.9 GB1911
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/starcoder2-7b-AWQ.

Rank the Starcoder2 7B AWQ 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer