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

Starcoder2 15B GPTQ by TechxGenus

 »  All LLMs  »  TechxGenus  »  Starcoder2 15B GPTQ   URL Share it on

  35   
  Arxiv:2004.05150   Arxiv:2205.14135   Arxiv:2207.14255   Arxiv:2305.13245   Arxiv:2402.19173   4-bit   Autotrain compatible   Code Dataset:bigcode/the-stack-v2-t...   Endpoints compatible   Gptq   Model-index   Quantized   Region:us   Safetensors   Starcoder2
Model Card on HF 🤗: https://huggingface.co/TechxGenus/starcoder2-15b-GPTQ 

Starcoder2 15B GPTQ Benchmarks

LLME Score: 0.14546
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starcoder2 15B GPTQ (TechxGenus/starcoder2-15b-GPTQ)
🌟 Advertise your project 🚀

Starcoder2 15B GPTQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
code generation
Applications:
programming
Primary Use Cases:
code completion, assisted coding
Limitations:
English predominantly, may contain bugs or be inefficient
Additional Notes 
The model supports generating code snippets from a wide range of programming languages, leveraging training on over 600 programming languages.
Supported Languages 
programming (>600)
Training Details 
Data Sources:
GitHub, Arxiv, Wikipedia
Data Volume:
>4 trillion tokens
Methodology:
Fill-in-the-Middle objective, 16,384-token context window with sliding window attention of 4,096 tokens
Context Length:
16384
Hardware Used:
NVIDIA DGX H100, NVIDIA Eos Supercomputer
Model Architecture:
Transformer decoder with grouped-query and sliding window attention
Input Output 
Input Format:
Tokenized code prompt
Accepted Modalities:
code snippets, programming scripts
Output Format:
Code completion or suggestion
Performance Tips:
Preprocessing inputs by following tokenization guidelines of the transformers library can enhance performance.
LLM NameStarcoder2 15B GPTQ
Repository 🤗https://huggingface.co/TechxGenus/starcoder2-15b-GPTQ 
Model Size15b
Required VRAM9.2 GB
Updated2025-09-23
MaintainerTechxGenus
Model Typestarcoder2
Model Files  9.2 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureStarcoder2ForCausalLM
Licensebigcode-openrail-m
Context Length16384
Model Max Length16384
Transformers Version4.39.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typefloat16

Best Alternatives to Starcoder2 15B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Starcoder2 15B Instruct GPTQ16K / 9.2 GB62
Speechless Starcoder2 15B16K / 31.9 GB6573
Starcoder2 15B16K / 63.8 GB6045635
Starcoder2 15B Instruct V0.116K / 31.9 GB2572102
Starcoder2 15B AWQ16K / 9.2 GB101
...rCoder2 15B Instruct V0.1 GGUF16K / 6.2 GB13710
StarCoder2 15B GGUF16K / 6.2 GB339028
Starchat2 15B V0.116K / 31.9 GB1377112
...rCoder2 15B Instruct V0.1 GGUF16K / 6.2 GB2270
Starcoder2 15B Finetuned Drake16K / 63.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/starcoder2-15b-GPTQ.

Rank the Starcoder2 15B 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? 51534 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