Skip to content
ModelListedExternal
Download

Dots Ocr Awq 4bit

This is a 4-bit AWQ quantized version of rednote-hilab/dots.ocr.

Sourcehuggingface.co/sugam24/dots-ocr-awq-4bit/tree/29f7c21827b21cbda94f6f5dc5577b8cf43ba0de
KindText modelBase modelrednote-hilab/dots.ocrVersionmodel

Model source

Kind
Text model
File size
2.11 GB
Base model
rednote-hilab/dots.ocr
Version
vmodel
Updated
Sep 26, 2026
Downloads
57
Tasks
Captioning
Source
Hugging Face

Source description

dots.ocr AWQ 4-bit Quantized

This is a 4-bit AWQ quantized version of rednote-hilab/dots.ocr.

Model Details

  • Base Model: rednote-hilab/dots.ocr
  • Quantization: W4A16 (4-bit weights, 16-bit activations)
  • Method: llm-compressor
  • Size: ~1.5GB (reduced from ~6GB)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor

model = AutoModelForCausalLM.from_pretrained(
    "sugam24/dots-ocr-awq-4bit",
    trust_remote_code=True,
    device_map="cuda"
)
tokenizer = AutoTokenizer.from_pretrained("sugam24/dots-ocr-awq-4bit", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("sugam24/dots-ocr-awq-4bit", trust_remote_code=True)

License

Same as the base model (Apache 2.0).

Sources

1 source
Hugging FacePrimaryVersion 29f7c21827b21cbda94f6f5dc5577b8cf43ba0de
huggingface.co/sugam24/dots-ocr-awq-4bit/tree/29f7c21827b21cbda94f6f5dc5577b8cf43ba0de

Verified Sep 11

Model artifacts

1 artifact

model.safetensors

safetensors · 2.11 GB · SHA-256 09d80309018c…f5ad · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 11huggingface.co/sugam24/dots-ocr-awq-4bit

--- license: apache-2.0 base_model: rednote-hilab/dots.ocr tags: - ocr - vision - quantized - awq - 4bit library_name: transformers pipeline_tag: image-to-text --- # dots.ocr AWQ 4-bit Quantized This is a 4-bit AWQ quantized version of [rednote-hilab/dots.ocr](https://huggingface.co/rednote-hilab/dots.ocr). ## Model Details - **Base Model**: rednote-hilab/dots.ocr - **Quantization**: W4A16 (4-bit weights, 16-bit activations) - **Method**: llm-compressor - **Size**: ~1.5GB (reduced from ~6GB) ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor model = AutoModelForCausalLM.from_pretrained( "sugam24/dots-ocr-awq-4bit", trust_remote_code=True, device_map="cuda" ) tokenizer = AutoTokenizer.from_pretrained("sugam24/dots-ocr-awq-4bit", trust_remote_code=True) processor = AutoProcessor.from_pretrained("sugam24/dots-ocr-awq-4bit", trust_remote_code=True) ``` ## License Same as the base model (Apache 2.0).

NoteSep 11huggingface.co/sugam24/dots-ocr-awq-4bit

Source context: 57 downloads · 1 likes · Pipeline image-to-text · Library transformers · Repo sugam24/dots-ocr-awq-4bit