Instructions to use emisilab/model-ocr-ktp-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emisilab/model-ocr-ktp-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="emisilab/model-ocr-ktp-v1")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("emisilab/model-ocr-ktp-v1")
model = AutoModelForMultimodalLM.from_pretrained("emisilab/model-ocr-ktp-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use emisilab/model-ocr-ktp-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emisilab/model-ocr-ktp-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emisilab/model-ocr-ktp-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/emisilab/model-ocr-ktp-v1

SGLang

How to use emisilab/model-ocr-ktp-v1 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 "emisilab/model-ocr-ktp-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emisilab/model-ocr-ktp-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "emisilab/model-ocr-ktp-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emisilab/model-ocr-ktp-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emisilab/model-ocr-ktp-v1 with Docker Model Runner:
```
docker model run hf.co/emisilab/model-ocr-ktp-v1
```

emisilab commited on Mar 25, 2024

Commit

468f91b

verified ·

1 Parent(s): 992fed4

Training in progress, epoch 1

Browse files

Files changed (4) hide show

config.json +1 -1
model.safetensors +1 -1
runs/Mar25_10-16-32_515a9fb0dfd2/events.out.tfevents.1711361798.515a9fb0dfd2.14131.0 +3 -0
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -188,5 +188,5 @@
   "pad_token_id": 1,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0"
 }

   "pad_token_id": 1,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
+  "transformers_version": "4.39.1"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37ee09dfcb9f86aa349f7ce4c8ee33077ca5807623128b66eab3276efff52b8
 size 809226392

 version https://git-lfs.github.com/spec/v1
+oid sha256:842fec74e97fd42f3f7e8c093a6bbd95dd7b56113a0e65171432013afdb2113d
 size 809226392

runs/Mar25_10-16-32_515a9fb0dfd2/events.out.tfevents.1711361798.515a9fb0dfd2.14131.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0999bb10827b88aae383364af37c379e50c478440b0de99670c565500ad9a859
+size 9263

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2c757b5c5de5fd9d298d9d1023c6c204516a16d81023b02dfd8e791bd87044
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:86f53e2142989ce91051a41f06ca08645e0b744ca3a0e3196adbbd463933aaf0
 size 4984