Instructions to use prithivMLmods/LatexMind-2B-Codec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/LatexMind-2B-Codec with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/LatexMind-2B-Codec")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("prithivMLmods/LatexMind-2B-Codec")
model = AutoModelForImageTextToText.from_pretrained("prithivMLmods/LatexMind-2B-Codec")
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 prithivMLmods/LatexMind-2B-Codec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/LatexMind-2B-Codec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/LatexMind-2B-Codec",
		"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/prithivMLmods/LatexMind-2B-Codec

SGLang

How to use prithivMLmods/LatexMind-2B-Codec 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 "prithivMLmods/LatexMind-2B-Codec" \
    --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": "prithivMLmods/LatexMind-2B-Codec",
		"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 "prithivMLmods/LatexMind-2B-Codec" \
        --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": "prithivMLmods/LatexMind-2B-Codec",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/LatexMind-2B-Codec with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/LatexMind-2B-Codec
```

prithivMLmods commited on Feb 1, 2025

Commit

7d7f72a

verified ·

1 Parent(s): 72b7cde

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -15,6 +15,8 @@ tags:
 ![qwenVL.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/g8zYbOSBt4NSqhSIypaX3.png)
 # **LatexMind-2B-Codec**
 The **LatexMind-2B-Codec** model is a fine-tuned version of Qwen2-VL-2B-Instruct, optimized for Optical Character Recognition (OCR), **image-to-text conversion**, and **mathematical expression extraction with LaTeX formatting**. This model integrates a conversational approach with visual and textual understanding to handle multi-modal tasks effectively.
@@ -113,9 +115,6 @@ print(output_text)
         buffer = buffer.replace("<|im_end|>", "")
         yield buffer
 ```
-Here’s the **Intended Use & Limitations** section for **LatexMind-2B-Codec**:
----
 # Intended Use

 ![qwenVL.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/g8zYbOSBt4NSqhSIypaX3.png)
+--------------
 # **LatexMind-2B-Codec**
 The **LatexMind-2B-Codec** model is a fine-tuned version of Qwen2-VL-2B-Instruct, optimized for Optical Character Recognition (OCR), **image-to-text conversion**, and **mathematical expression extraction with LaTeX formatting**. This model integrates a conversational approach with visual and textual understanding to handle multi-modal tasks effectively.
         buffer = buffer.replace("<|im_end|>", "")
         yield buffer
 ```
 # Intended Use