VisCoder 7B by TIGER-Lab

 ยป  All LLMs  ยป  TIGER-Lab  ยป  VisCoder 7B   URL Share it on

  Arxiv:2506.03930   Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-...   Code   Codegen   Conversational   Dataset:tiger-lab/viscode-200k   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/TIGER-Lab/VisCoder-7B 

VisCoder 7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
VisCoder 7B (TIGER-Lab/VisCoder-7B)
๐ŸŒŸ Advertise your project ๐Ÿš€

VisCoder 7B Parameters and Internals

LLM NameVisCoder 7B
Repository ๐Ÿค—https://huggingface.co/TIGER-Lab/VisCoder-7B 
Base Model(s)  Qwen/Qwen2.5-Coder-7B-Instruct   Qwen/Qwen2.5-Coder-7B-Instruct
Model Size7b
Required VRAM15.2 GB
Updated2025-07-20
MaintainerTIGER-Lab
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to VisCoder 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Rebase986K / 15.2 GB732
Qwen2.5 7B Rebase986K / 15.2 GB62
StockQwen 2.5 7B128K / 15.2 GB75
Tessa T1 7B117K / 15.2 GB2110
UIGEN T1.5 7B117K / 15.2 GB146
Qwen2.5 Coder 7B Instruct32K / 15.2 GB212829509
Arch Agent 7B32K / 15.2 GB49741
Qwen2.5 7B MS Destroyer32K / 15.2 GB41
Viper Coder HybridMini V1.332K / 15.2 GB458
Qwen2.5 MFANN 7B SLERP V1.232K / 14.8 GB210
Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/VisCoder-7B.

Rank the VisCoder 7B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 49901 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124