Instructions to use keystats/Legend_ocr_llama3.2_11b_vision_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keystats/Legend_ocr_llama3.2_11b_vision_lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
model = PeftModel.from_pretrained(base_model, "keystats/Legend_ocr_llama3.2_11b_vision_lora")

Transformers

How to use keystats/Legend_ocr_llama3.2_11b_vision_lora with Transformers:

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

pipe = pipeline("text-generation", model="keystats/Legend_ocr_llama3.2_11b_vision_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("keystats/Legend_ocr_llama3.2_11b_vision_lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keystats/Legend_ocr_llama3.2_11b_vision_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keystats/Legend_ocr_llama3.2_11b_vision_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keystats/Legend_ocr_llama3.2_11b_vision_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/keystats/Legend_ocr_llama3.2_11b_vision_lora

SGLang

How to use keystats/Legend_ocr_llama3.2_11b_vision_lora 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 "keystats/Legend_ocr_llama3.2_11b_vision_lora" \
    --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": "keystats/Legend_ocr_llama3.2_11b_vision_lora",
		"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 "keystats/Legend_ocr_llama3.2_11b_vision_lora" \
        --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": "keystats/Legend_ocr_llama3.2_11b_vision_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keystats/Legend_ocr_llama3.2_11b_vision_lora with Docker Model Runner:
```
docker model run hf.co/keystats/Legend_ocr_llama3.2_11b_vision_lora
```

Legend_ocr_llama3.2_11b_vision_lora / processor_config.json

keystats

Llama-3.2-11B-Vision LoRA OCR, step 150, val score 0.8630

a125f75 verified 21 days ago

Raw History Blame Contribute Delete

550 Bytes

{
  "image_processor": {
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": true,
    "do_rescale": true,
    "do_resize": true,
    "image_mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "image_processor_type": "MllamaImageProcessor",
    "image_std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "max_image_tiles": 4,
    "resample": 2,
    "rescale_factor": 0.00392156862745098,
    "size": {
      "height": 560,
      "width": 560
    }
  },
  "processor_class": "MllamaProcessor"
}

	{
	"image_processor": {
	"do_convert_rgb": true,
	"do_normalize": true,
	"do_pad": true,
	"do_rescale": true,
	"do_resize": true,
	"image_mean": [
	0.48145466,
	0.4578275,
	0.40821073
	],
	"image_processor_type": "MllamaImageProcessor",
	"image_std": [
	0.26862954,
	0.26130258,
	0.27577711
	],
	"max_image_tiles": 4,
	"resample": 2,
	"rescale_factor": 0.00392156862745098,
	"size": {
	"height": 560,
	"width": 560
	}
	},
	"processor_class": "MllamaProcessor"
	}