Arxiv:2506.02295 4bit Ar Base model:adapter:unsloth/qwe... Base model:unsloth/qwen2-vl-2b... Conversational Image-text-to-text Instruct Lora Ocr Peft Quantized Qwen2 vl Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct
Qari OCR 0.2.2.1 VL 2B Instruct Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qari OCR 0.2.2.1 VL 2B Instruct Parameters and Internals
| LLM Name | Qari OCR 0.2.2.1 VL 2B Instruct |
| Repository 🤗 | https://huggingface.co/NAMAA-Space/Qari-OCR-0.2.2.1-VL-2B-Instruct |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 0.1 GB |
| Updated | 2025-10-05 |
| Maintainer | NAMAA-Space |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ar |
| Quantization Type | 4bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | (|?|:|.|*|?|(|?|:|v|i|s|i|o|n|||i|m|a|g|e|||v|i|s|u|a|l|||p|a|t|c|h|||l|a|n|g|u|a|g|e|||t|e|x|t|)|.|*|?|(|?|:|s|e|l|f|_|a|t|t|n|||a|t|t|e|n|t|i|o|n|||a|t|t|n|||m|l|p|||f|e|e|d|_|f|o|r|w|a|r|d|||f|f|n|||d|e|n|s|e|)|.|*|?|(|?|:|q|k|v|||p|r|o|j|||f|c|1|||f|c|2|||q|_|p|r|o|j|||k|_|p|r|o|j|||v|_|p|r|o|j|||o|_|p|r|o|j|||g|a|t|e|_|p|r|o|j|||u|p|_|p|r|o|j|||d|o|w|n|_|p|r|o|j|)|.|*|?|)|||(|?|:|\|b|m|o|d|e|l|\|.|l|a|y|e|r|s|\|.|[|\|d|]|{|1|,|}|\|.|(|?|:|s|e|l|f|_|a|t|t|n|||a|t|t|e|n|t|i|o|n|||a|t|t|n|||m|l|p|||f|e|e|d|_|f|o|r|w|a|r|d|||f|f|n|||d|e|n|s|e|)|\|.|(|?|:|(|?|:|q|k|v|||p|r|o|j|||f|c|1|||f|c|2|||q|_|p|r|o|j|||k|_|p|r|o|j|||v|_|p|r|o|j|||o|_|p|r|o|j|||g|a|t|e|_|p|r|o|j|||u|p|_|p|r|o|j|||d|o|w|n|_|p|r|o|j|)|)|) |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
| Errors | replace |
Best Alternatives to Qari OCR 0.2.2.1 VL 2B Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...emma 2B Finetuned Sft Navarasa | 0K / 0.3 GB | 0 | 6 |
| Telugu Gemma 2B Finetuned Sft | 0K / 0.3 GB | 0 | 3 |
Rank the Qari OCR 0.2.2.1 VL 2B Instruct 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! 🌟
What open-source LLMs or SLMs are you in search of? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124