Instructions to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Remidesbois/hunyuanocr-1.5-poneglyph-bbox")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Remidesbois/hunyuanocr-1.5-poneglyph-bbox")
model = AutoModelForMultimodalLM.from_pretrained("Remidesbois/hunyuanocr-1.5-poneglyph-bbox", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox 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 Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
# Run inference directly in the terminal:
llama cli -hf Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
# Run inference directly in the terminal:
llama cli -hf Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

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 Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
# Run inference directly in the terminal:
./llama-cli -hf Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

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 Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

Use Docker

docker model run hf.co/Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

LM Studio
Jan

vLLM

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Remidesbois/hunyuanocr-1.5-poneglyph-bbox"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Remidesbois/hunyuanocr-1.5-poneglyph-bbox",
		"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/Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

SGLang

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Remidesbois/hunyuanocr-1.5-poneglyph-bbox" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Remidesbois/hunyuanocr-1.5-poneglyph-bbox",
		"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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Remidesbois/hunyuanocr-1.5-poneglyph-bbox" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Remidesbois/hunyuanocr-1.5-poneglyph-bbox",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with Ollama:
```
ollama run hf.co/Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
```

Unsloth Studio

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox 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 Remidesbois/hunyuanocr-1.5-poneglyph-bbox 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 Remidesbois/hunyuanocr-1.5-poneglyph-bbox to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Remidesbois/hunyuanocr-1.5-poneglyph-bbox to start chatting

Docker Model Runner
How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with Docker Model Runner:
```
docker model run hf.co/Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16
```

Lemonade

How to use Remidesbois/hunyuanocr-1.5-poneglyph-bbox with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Remidesbois/hunyuanocr-1.5-poneglyph-bbox:BF16

Run and chat with the model

lemonade run user.hunyuanocr-1.5-poneglyph-bbox-BF16

List all available models

lemonade list

Atomic Chat

Remidesbois commited on 26 days ago

Commit

df3ce38

verified ·

1 Parent(s): 319f5ab

Add files using upload-large-folder tool

Browse files

Files changed (23) hide show

.gitattributes +22 -0
gguf/hyocr-bbox-f16.gguf +3 -0
gguf/mmproj-hyocr-bbox-f16.gguf +3 -0
runtime/ggml-cpu-alderlake.dll +3 -0
runtime/ggml-cpu-cannonlake.dll +3 -0
runtime/ggml-cpu-cascadelake.dll +3 -0
runtime/ggml-cpu-cooperlake.dll +3 -0
runtime/ggml-cpu-haswell.dll +3 -0
runtime/ggml-cpu-icelake.dll +3 -0
runtime/ggml-cpu-ivybridge.dll +3 -0
runtime/ggml-cpu-piledriver.dll +3 -0
runtime/ggml-cpu-sandybridge.dll +3 -0
runtime/ggml-cpu-sapphirerapids.dll +3 -0
runtime/ggml-cpu-skylakex.dll +3 -0
runtime/ggml-cpu-sse42.dll +3 -0
runtime/ggml-cpu-x64.dll +3 -0
runtime/ggml-cpu-zen4.dll +3 -0
runtime/ggml-cuda.dll +3 -0
runtime/ggml-rpc-server.exe +3 -0
runtime/ggml-rpc.dll +3 -0
runtime/libomp140.x86_64.dll +3 -0
runtime/llama-bench-impl.dll +3 -0
runtime/llama-common.dll +3 -0

@@ -48,3 +48,25 @@ runtime/cublas64_12.dll filter=lfs diff=lfs merge=lfs -text
 runtime/cudart64_12.dll filter=lfs diff=lfs merge=lfs -text
 runtime/cublasLt64_12.dll filter=lfs diff=lfs merge=lfs -text
 runtime/ggml-base.dll filter=lfs diff=lfs merge=lfs -text

 runtime/cudart64_12.dll filter=lfs diff=lfs merge=lfs -text
 runtime/cublasLt64_12.dll filter=lfs diff=lfs merge=lfs -text
 runtime/ggml-base.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cuda.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-alderlake.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-cannonlake.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-cascadelake.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-cooperlake.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-haswell.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-icelake.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-ivybridge.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-piledriver.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-sandybridge.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-sapphirerapids.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-skylakex.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-sse42.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-x64.dll filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-cpu-zen4.dll filter=lfs diff=lfs merge=lfs -text
+gguf/hyocr-bbox-f16.gguf filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-rpc-server.exe filter=lfs diff=lfs merge=lfs -text
+runtime/ggml-rpc.dll filter=lfs diff=lfs merge=lfs -text
+runtime/libomp140.x86_64.dll filter=lfs diff=lfs merge=lfs -text
+runtime/llama-bench-impl.dll filter=lfs diff=lfs merge=lfs -text
+gguf/mmproj-hyocr-bbox-f16.gguf filter=lfs diff=lfs merge=lfs -text
+runtime/llama-common.dll filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:98959002436329ed49b683dd98c4f7bd14fb6fb7a3689b7e729f84357ce76ad3
+size 1083218528

+version https://git-lfs.github.com/spec/v1
+oid sha256:04ae55ed197d0b3a47db8aa5fcfe29db80ba55634683d11b9fdd6a0e9ca27266
+size 952999008

+version https://git-lfs.github.com/spec/v1
+oid sha256:559368de2f057eee272f391f4841c1af4bf7fe4acec2e26ad6c59cba702bb0f4
+size 1165824

+version https://git-lfs.github.com/spec/v1
+oid sha256:172490cc2dab24c112bc19ffa9db3c9199241c7f2ec5e676c8f827df46453bbb
+size 1381376

+version https://git-lfs.github.com/spec/v1
+oid sha256:2500ccea0f8896e067c30bef35676b3bff459a27f22f793db119b91e18e4b7b1
+size 1367552

+version https://git-lfs.github.com/spec/v1
+oid sha256:08a924c4ae045b855341afa129b5f1877f6ce3409d2b5f65082f4a63e865180b
+size 1368064

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e77fe4f66ef55b84ef18487a0ddcd003e5ca31ecde6382262ae3f6fed99ba5
+size 1170432

+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0333aa89ce7db925018b2ca1bc101aba87f6023c49e4d7855516c76582780a
+size 1374208

+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b8295699007631deb26195b69982156cac6b7b792b6a93760c829716e4ecb3
+size 1059328

+version https://git-lfs.github.com/spec/v1
+oid sha256:92b22e1daefd0494d37c376779644678c14ff423cec386746ef06dc6e4e3496d
+size 1062400

	@@ -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:b3c038549655435f48cb4629d14e6e861c0b5c622482733d4f1f7c80f02ae35a
+size 1039872

+version https://git-lfs.github.com/spec/v1
+oid sha256:42b375746822d9d716802db17c37606d9565dbf76fe9b28aebd2fc4f073587ec
+size 1645056

+version https://git-lfs.github.com/spec/v1
+oid sha256:0c93a0c50c6c72a2370e1411901f72cd2ddca547a90117afeb76b6e78c144cb3
+size 1374720

+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c3c73856676296de28948dfff2afcf6751ec379db3dc42954adaaece9292a7
+size 862720

+version https://git-lfs.github.com/spec/v1
+oid sha256:b17ef586ff5c5341b3522966f3ccbdad579c7855e81f3f7e6ffb61e3dcf9d1f2
+size 857600

+version https://git-lfs.github.com/spec/v1
+oid sha256:f62daade0bfd0191152af42ac75718a4a42bb0ad66b671e3ade860d305961402
+size 576482816

+version https://git-lfs.github.com/spec/v1
+oid sha256:820aff6a122cd65135ad75a1b382869604c9a1b89ee8c07ad7fd06432a91e630
+size 101376

+version https://git-lfs.github.com/spec/v1
+oid sha256:435fdab149550377c272bf002ea3f761e2534074aaa5c880ab2e0c97c6a2198b
+size 136192

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a20c1e5c115c29771a12324513eb109badac72180f79481527ad79d996ffb33
+size 661856

+version https://git-lfs.github.com/spec/v1
+oid sha256:adea0438d9d142e74318a154b97b8aa33ac49c75f24f199fd1e8ac91681521e2
+size 392192

+version https://git-lfs.github.com/spec/v1
+oid sha256:19f4f8b3f7a1afcd6f5047603022ccabd8d939e2fa666ec9018344109400006d
+size 7941120