Instructions to use dragonstar/image-text-captcha-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dragonstar/image-text-captcha-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="dragonstar/image-text-captcha-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("dragonstar/image-text-captcha-v2")
model = AutoModelForImageTextToText.from_pretrained("dragonstar/image-text-captcha-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dragonstar/image-text-captcha-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dragonstar/image-text-captcha-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dragonstar/image-text-captcha-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dragonstar/image-text-captcha-v2

SGLang

How to use dragonstar/image-text-captcha-v2 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 "dragonstar/image-text-captcha-v2" \
    --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": "dragonstar/image-text-captcha-v2",
		"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 "dragonstar/image-text-captcha-v2" \
        --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": "dragonstar/image-text-captcha-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dragonstar/image-text-captcha-v2 with Docker Model Runner:
```
docker model run hf.co/dragonstar/image-text-captcha-v2
```

dragonstar commited on Jun 2, 2023

Commit

caa3080

1 Parent(s): 746902d

Model save

Browse files

Files changed (2) hide show

generation_config.json +13 -0
runs/Jun02_22-02-48_da6a3a754f20/events.out.tfevents.1685743382.da6a3a754f20.1065.0 +2 -2

generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.2",
+  "use_cache": false
+}

runs/Jun02_22-02-48_da6a3a754f20/events.out.tfevents.1685743382.da6a3a754f20.1065.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a43a3fee90029e1a1b6e3db0e7b0d6ff410b8fba521ab990167d78c43626ed
-size 10618

 version https://git-lfs.github.com/spec/v1
+oid sha256:bafd4653c08f6890ec753b6ad7f5993aa30937203eb2f498db109b57627699a2
+size 10972