Instructions to use marioVIC/arabic-semantic-chunking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marioVIC/arabic-semantic-chunking with Transformers:

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

pipe = pipeline("text-generation", model="marioVIC/arabic-semantic-chunking")
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("marioVIC/arabic-semantic-chunking")
model = AutoModelForMultimodalLM.from_pretrained("marioVIC/arabic-semantic-chunking", 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

vLLM

How to use marioVIC/arabic-semantic-chunking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "marioVIC/arabic-semantic-chunking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "marioVIC/arabic-semantic-chunking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/marioVIC/arabic-semantic-chunking

SGLang

How to use marioVIC/arabic-semantic-chunking 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 "marioVIC/arabic-semantic-chunking" \
    --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": "marioVIC/arabic-semantic-chunking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "marioVIC/arabic-semantic-chunking" \
        --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": "marioVIC/arabic-semantic-chunking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use marioVIC/arabic-semantic-chunking with Docker Model Runner:
```
docker model run hf.co/marioVIC/arabic-semantic-chunking
```

marioVIC commited on Apr 5

Commit

fe58e69

verified ·

1 Parent(s): d21301f

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "o_proj",
     "gate_proj",
-    "k_proj",
     "v_proj",
-    "q_proj",
-    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
+    "up_proj",
+    "q_proj",
     "gate_proj",
     "v_proj",
+    "down_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6ae39d54027c091bbbb89193b60af48a7e3cc4ea1474c6f48f933fbafdc47e
 size 131252288

 version https://git-lfs.github.com/spec/v1
+oid sha256:0af23d2f56497e79abbdc34fd098805cfc7048d79eef674e91c6f39570e2ca1a
 size 131252288