Instructions to use sahilchachra/Unlimited-OCR-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use sahilchachra/Unlimited-OCR-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use sahilchachra/Unlimited-OCR-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sahilchachra/Unlimited-OCR-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sahilchachra/Unlimited-OCR-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Ollama
How to use sahilchachra/Unlimited-OCR-GGUF with Ollama:
```
ollama run hf.co/sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use sahilchachra/Unlimited-OCR-GGUF with Docker Model Runner:
```
docker model run hf.co/sahilchachra/Unlimited-OCR-GGUF:Q4_K_M
```

Lemonade

How to use sahilchachra/Unlimited-OCR-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sahilchachra/Unlimited-OCR-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Unlimited-OCR-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

sahilchachra commited on Jul 1

Commit

0dc781d

verified ·

1 Parent(s): 028d046

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -7

README.md CHANGED Viewed

@@ -86,11 +86,9 @@ Run it on an image:
   --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
   --image document.png \
   -p "<|grounding|>Convert the document to markdown." \
-  --chat-template deepseek-ocr --temp 0
 ```
-> `--chat-template deepseek-ocr` and `--mmproj` are **required**. With `--image`, the image is
-> injected automatically — you do **not** need to type a literal `<image>` token in `-p`.
 > Use `--temp 0` for OCR (deterministic). Add `-n 4096` (or more) for long/dense documents.
 ---
@@ -115,7 +113,7 @@ prefix it with `<|grounding|>` whenever you also want **bounding boxes** for wha
 **1) Document → clean Markdown (tables, headings, reading order):**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
-  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf --chat-template deepseek-ocr \
   --image invoice.png --temp 0 -n 4096 \
   -p "<|grounding|>Convert the document to markdown."
 ```
@@ -123,14 +121,14 @@ prefix it with `<|grounding|>` whenever you also want **bounding boxes** for wha
 **2) Just the raw text, no layout / no boxes:**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
-  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf --chat-template deepseek-ocr \
   --image receipt.jpg --temp 0 -p "Free OCR."
 ```
 **3) Locate a specific string and get its box:**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
-  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf --chat-template deepseek-ocr \
   --image form.png --temp 0 \
   -p "<|grounding|>Locate <|ref|>Invoice Number<|/ref|> in the image."
 ```
@@ -162,7 +160,7 @@ plain text (or Markdown) with no box tags.
 ./build/bin/llama-server \
   -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
   --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
-  --chat-template deepseek-ocr -c 8192 --host 0.0.0.0 --port 8080
 ```
 Call it with an image (base64 data URL):

   --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
   --image document.png \
   -p "<|grounding|>Convert the document to markdown." \
+  --temp 0
 ```
 > Use `--temp 0` for OCR (deterministic). Add `-n 4096` (or more) for long/dense documents.
 ---
 **1) Document → clean Markdown (tables, headings, reading order):**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
+  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
   --image invoice.png --temp 0 -n 4096 \
   -p "<|grounding|>Convert the document to markdown."
 ```
 **2) Just the raw text, no layout / no boxes:**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
+  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
   --image receipt.jpg --temp 0 -p "Free OCR."
 ```
 **3) Locate a specific string and get its box:**
 ```bash
 ./build/bin/llama-mtmd-cli -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
+  --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
   --image form.png --temp 0 \
   -p "<|grounding|>Locate <|ref|>Invoice Number<|/ref|> in the image."
 ```
 ./build/bin/llama-server \
   -m ./uocr/Unlimited-OCR-Q4_K_M.gguf \
   --mmproj ./uocr/mmproj-Unlimited-OCR-F16.gguf \
+  -c 8192 --host 0.0.0.0 --port 8080
 ```
 Call it with an image (base64 data URL):