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

Libraries

How to use mradermacher/HunyuanOCR-GGUF with Transformers:

# Use a pipeline as a high-level helper
# Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("image-to-text", model="mradermacher/HunyuanOCR-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/HunyuanOCR-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/HunyuanOCR-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/HunyuanOCR-GGUF",
	filename="HunyuanOCR.IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "\"cats.jpg\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/HunyuanOCR-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/HunyuanOCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/HunyuanOCR-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/HunyuanOCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/HunyuanOCR-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 mradermacher/HunyuanOCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/HunyuanOCR-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 mradermacher/HunyuanOCR-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/HunyuanOCR-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/HunyuanOCR-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/HunyuanOCR-GGUF with Ollama:
```
ollama run hf.co/mradermacher/HunyuanOCR-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mradermacher/HunyuanOCR-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/HunyuanOCR-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/HunyuanOCR-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/HunyuanOCR-GGUF to start chatting

Docker Model Runner
How to use mradermacher/HunyuanOCR-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/HunyuanOCR-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/HunyuanOCR-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/HunyuanOCR-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.HunyuanOCR-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Apr 7

Commit

7b4277b

verified ·

1 Parent(s): 6089a08

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
HunyuanOCR.IQ4_XS.gguf +3 -0
HunyuanOCR.Q2_K.gguf +3 -0
HunyuanOCR.Q3_K_L.gguf +3 -0
HunyuanOCR.Q3_K_M.gguf +3 -0
HunyuanOCR.Q3_K_S.gguf +3 -0
HunyuanOCR.Q4_K_M.gguf +3 -0
HunyuanOCR.Q4_K_S.gguf +3 -0
HunyuanOCR.Q5_K_M.gguf +3 -0
HunyuanOCR.Q5_K_S.gguf +3 -0
HunyuanOCR.Q6_K.gguf +3 -0
HunyuanOCR.Q8_0.gguf +3 -0
HunyuanOCR.f16.gguf +3 -0

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 HunyuanOCR.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
 HunyuanOCR.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 HunyuanOCR.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
 HunyuanOCR.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+HunyuanOCR.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:e746a21b568bd1078dc6ed312ac3572019c5882baee2992887d3369ca5dde0c6
+size 329113088

+version https://git-lfs.github.com/spec/v1
+oid sha256:faf627a5134e0bc643740150204dd1393ec34d89ee80fb83559a4a4c592264ba
+size 259661312

+version https://git-lfs.github.com/spec/v1
+oid sha256:a445ae98522b2de1e5839bfa2b1f2d18e4e8a0580605a26002e6ec10f4723c59
+size 327392768

+version https://git-lfs.github.com/spec/v1
+oid sha256:d82aed19094b5c9360c7a94d70280ad3ae1e3ce5afdb3afced6419452187283e
+size 307666432

+version https://git-lfs.github.com/spec/v1
+oid sha256:b44649df28d7c743e2ddecff23ae39fb1f7c4639da6796214ea23ee89574725b
+size 285220352

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2378d06e4b56aae46b9db5f8beb19d34a719b564c7c6106f161d56fd548bed
+size 354967040

+version https://git-lfs.github.com/spec/v1
+oid sha256:1326cedb90ddadc69459c38c2baf56463b4f7b2819aa12948f64eea334ea3274
+size 342269440

+version https://git-lfs.github.com/spec/v1
+oid sha256:69df7c5d61aa7e7cf7dad81ffc3fe096306dd60150d6a9dc1749f0d06f1fb726
+size 399793664

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e01cf5a1e00464ce9c3e17fc6a9b4f1372b02fdc2cefab7117ea0703d1be81
+size 392273408

+version https://git-lfs.github.com/spec/v1
+oid sha256:a60dde791fabb6c042bbea5d4be79e43da1e8a08f773d7c1e2825d282e084e13
+size 447421952

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff79d146bda6f4015a9c7ea382b3699c502ab90c1b5661d6f96808583e6a947
+size 577949792

+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd818dce14909eca20fc9d82b352c3b0419a63a7d20c0f411f609231d6a80ea
+size 1083218912