benhaotang/Nanonets-OCR-s:q4_k

benhaotang/

Nanonets-OCR-s:q4_k_m

5,484 Downloads Updated 2 months ago

OCR model by Nanonets that excels at turning anything into markdown

vision

Updated 3 months ago

3 months ago

34eee06c6728 · 3.2GB

model

archqwen25vl

parameters3.75B

quantizationQ4_K_M

3.2GB

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ range .Messages }}{{ if eq .R

254B

system

Extract the text from the above document as if you were reading it naturally. Return the tables in h

586B

params

{ "num_ctx": 4096, "stop": [ "<|im_end|>" ] }

49B

Readme

Quatized nanonets/Nanonets-OCR-s with ollama 0.8.0, a 6GB card can safely run this model at Q8

I only recommend running the default Q8 version unless RAM constrains, as Q4_K_M shows a notable degradation of performance in code block recognition

Nanonets-OCR-s demonstrates strong OCR ability across different domains, turns anything into markdown with proper math and todo list support, following are two examples generated with ollama 0.8.0 embeded in Msty