Tiny Agent A 3B by driaforall

 ยป  All LLMs  ยป  driaforall  ยป  Tiny Agent A 3B   URL Share it on

  Arxiv:2303.17760   Arxiv:2408.02442   Arxiv:2408.08435   Arxiv:2410.02089   Arxiv:2411.01747   Agent   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-coder-...   Chat   Code   Codegen   Conversational   En   Endpoints compatible   Gguf   Instruct   Quantized   Qwen   Qwen-coder   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Tiny Agent A 3B Benchmarks

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

Tiny Agent A 3B Parameters and Internals

LLM NameTiny Agent A 3B
Repository ๐Ÿค—https://huggingface.co/driaforall/Tiny-Agent-a-3B 
Base Model(s)  Qwen/Qwen2.5-Coder-3B-Instruct   Qwen/Qwen2.5-Coder-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2025-06-09
Maintainerdriaforall
Model Typeqwen2
Instruction-BasedYes
Model Files  1.9 GB   3.3 GB   5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace
Tiny Agent A 3B (driaforall/Tiny-Agent-a-3B)

Best Alternatives to Tiny Agent A 3B

Best Alternatives
Context / RAM
Downloads
Likes
Coder GRPO 3B32K / 6.2 GB8031
...2.5 Coder 3B Instruct Bnb 4bit32K / 2 GB85714
Qwen3b Lora Finetune32K / 6.2 GB01
Tessa T1 3B117K / 6.2 GB113
UIGEN T1.5 3B117K / 6.2 GB101
Qwen2.5 Coder 3B Instruct32K / 6.2 GB3854958
Qwen 2.5 3b Smarteaz 0.01a32K / 6.3 GB161
Q2.5 CodeR1 3B32K / 6.2 GB161
Qwen2.5 Coder 3B Instruct AWQ32K / 2.7 GB470234
Arch Function Chat 3B32K / 6.2 GB2620
Note: green Score (e.g. "73.2") means that the model is better than driaforall/Tiny-Agent-a-3B.

Rank the Tiny Agent A 3B 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? 48046 in total.

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