Camel-Doc-OCR-062825-mmp-GGUF

The Camel-Doc-OCR-062825 model is a fine-tuned version of Qwen2.5-VL-7B-Instruct, optimized for Document Retrieval, Content Extraction, and Analysis Recognition. Built on top of the Qwen2.5-VL architecture, this model enhances document comprehension capabilities with focused training on the Opendoc2-Analysis-Recognition dataset for superior document analysis and information extraction tasks.

Model Files

File Name	Size	Type	Description
Camel-Doc-OCR-062825.Q2_K.gguf	3.02 GB	Model	Q2_K quantized model
Camel-Doc-OCR-062825.Q3_K_M.gguf	3.81 GB	Model	Q3_K_M quantized model
Camel-Doc-OCR-062825.Q4_K_M.gguf	4.68 GB	Model	Q4_K_M quantized model
Camel-Doc-OCR-062825.Q5_K_M.gguf	5.44 GB	Model	Q5_K_M quantized model
Camel-Doc-OCR-062825.Q6_K.gguf	6.25 GB	Model	Q6_K quantized model
Camel-Doc-OCR-062825.Q8_0.gguf	8.1 GB	Model	Q8_0 quantized model
Camel-Doc-OCR-062825.f16.gguf	15.2 GB	Model	Full precision f16 model
Camel-Doc-OCR-062825.mmproj-Q8_0.gguf	853 MB	Projection	Q8_0 multimodal projection
Camel-Doc-OCR-062825.mmproj-f16.gguf	1.35 GB	Projection	f16 multimodal projection
.gitattributes	2.14 kB	Config	Git LFS configuration
config.json	36 Bytes	Config	Model configuration
README.md	633 Bytes	Documentation	Repository documentation

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):