Instructions to use kacperwikiel/polish-ocr-lora-broken with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kacperwikiel/polish-ocr-lora-broken with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("PaddlePaddle/PaddleOCR-VL")
model = PeftModel.from_pretrained(base_model, "kacperwikiel/polish-ocr-lora-broken")

Transformers

How to use kacperwikiel/polish-ocr-lora-broken with Transformers:

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

pipe = pipeline("image-text-to-text", model="kacperwikiel/polish-ocr-lora-broken")
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 AutoModel
model = AutoModel.from_pretrained("kacperwikiel/polish-ocr-lora-broken", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kacperwikiel/polish-ocr-lora-broken with vLLM:

Install from pip and serve model

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

SGLang

How to use kacperwikiel/polish-ocr-lora-broken 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 "kacperwikiel/polish-ocr-lora-broken" \
    --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": "kacperwikiel/polish-ocr-lora-broken",
		"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 "kacperwikiel/polish-ocr-lora-broken" \
        --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": "kacperwikiel/polish-ocr-lora-broken",
		"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 kacperwikiel/polish-ocr-lora-broken with Docker Model Runner:
```
docker model run hf.co/kacperwikiel/polish-ocr-lora-broken
```

polish-ocr-lora-broken / checkpoint-50 /trainer_state.json

anon

Upload folder using huggingface_hub

ceb5cc2 verified 5 months ago

raw

history blame contribute delete

1.65 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.17761989342806395,
	"eval_steps": 200,
	"global_step": 50,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.035523978685612786,
	"grad_norm": 30.68755531311035,
	"learning_rate": 2.1176470588235296e-05,
	"loss": 10.0284,
	"step": 10
	},
	{
	"epoch": 0.07104795737122557,
	"grad_norm": 11.449149131774902,
	"learning_rate": 4.470588235294118e-05,
	"loss": 8.8672,
	"step": 20
	},
	{
	"epoch": 0.10657193605683836,
	"grad_norm": 8.332048416137695,
	"learning_rate": 6.823529411764707e-05,
	"loss": 7.2862,
	"step": 30
	},
	{
	"epoch": 0.14209591474245115,
	"grad_norm": 8.64196491241455,
	"learning_rate": 9.176470588235295e-05,
	"loss": 5.7446,
	"step": 40
	},
	{
	"epoch": 0.17761989342806395,
	"grad_norm": 9.184565544128418,
	"learning_rate": 0.00011529411764705881,
	"loss": 4.3277,
	"step": 50
	}
	],
	"logging_steps": 10,
	"max_steps": 846,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 3,
	"save_steps": 50,
	"stateful_callbacks": {
	"TrainerControl": {
	"args": {
	"should_epoch_stop": false,
	"should_evaluate": false,
	"should_log": false,
	"should_save": true,
	"should_training_stop": false
	},
	"attributes": {}
	}
	},
	"total_flos": 2018622500093952.0,
	"train_batch_size": 16,
	"trial_name": null,
	"trial_params": null
	}