Instructions to use ayoubkirouane/moondream2-image-captcha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayoubkirouane/moondream2-image-captcha with Transformers:

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

pipe = pipeline("image-text-to-text", model="ayoubkirouane/moondream2-image-captcha", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ayoubkirouane/moondream2-image-captcha", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ayoubkirouane/moondream2-image-captcha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayoubkirouane/moondream2-image-captcha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayoubkirouane/moondream2-image-captcha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ayoubkirouane/moondream2-image-captcha

SGLang

How to use ayoubkirouane/moondream2-image-captcha 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 "ayoubkirouane/moondream2-image-captcha" \
    --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": "ayoubkirouane/moondream2-image-captcha",
		"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 "ayoubkirouane/moondream2-image-captcha" \
        --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": "ayoubkirouane/moondream2-image-captcha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ayoubkirouane/moondream2-image-captcha with Docker Model Runner:
```
docker model run hf.co/ayoubkirouane/moondream2-image-captcha
```

ayoubkirouane commited on May 22, 2024

Commit

664660a

verified ·

1 Parent(s): f61ce7e

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

config.json +4 -3
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -1,15 +1,16 @@
 {
   "architectures": [
     "Moondream"
   ],
   "auto_map": {
-    "AutoConfig": "configuration_moondream.MoondreamConfig",
-    "AutoModelForCausalLM": "moondream.Moondream"
   },
   "model_type": "moondream1",
   "text_config": {
     "model_type": "phi"
   },
   "torch_dtype": "float16",
-  "transformers_version": "4.38.2"
 }

 {
+  "_name_or_path": "vikhyatk/moondream2",
   "architectures": [
     "Moondream"
   ],
   "auto_map": {
+    "AutoConfig": "vikhyatk/moondream2--configuration_moondream.MoondreamConfig",
+    "AutoModelForCausalLM": "vikhyatk/moondream2--moondream.Moondream"
   },
   "model_type": "moondream1",
   "text_config": {
     "model_type": "phi"
   },
   "torch_dtype": "float16",
+  "transformers_version": "4.41.0"
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.38.2"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "4.41.0"
 }