Instructions to use nkim7/eval3_phase2_TOY with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use nkim7/eval3_phase2_TOY with PEFT:
```
Task type is invalid.
```

How to use nkim7/eval3_phase2_TOY with Transformers:

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

pipe = pipeline("text-generation", model="nkim7/eval3_phase2_TOY")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nkim7/eval3_phase2_TOY", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nkim7/eval3_phase2_TOY with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nkim7/eval3_phase2_TOY"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nkim7/eval3_phase2_TOY",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nkim7/eval3_phase2_TOY

SGLang

How to use nkim7/eval3_phase2_TOY 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 "nkim7/eval3_phase2_TOY" \
    --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": "nkim7/eval3_phase2_TOY",
		"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 "nkim7/eval3_phase2_TOY" \
        --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": "nkim7/eval3_phase2_TOY",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nkim7/eval3_phase2_TOY with Docker Model Runner:
```
docker model run hf.co/nkim7/eval3_phase2_TOY
```

eval3_phase2_TOY

File size: 944 Bytes

1fa04ae

{
  "crop_size": null,
  "data_format": "channels_first",
  "default_to_square": true,
  "device": null,
  "do_center_crop": null,
  "do_convert_rgb": true,
  "do_image_splitting": true,
  "do_normalize": true,
  "do_pad": true,
  "do_rescale": true,
  "do_resize": true,
  "do_sample_frames": false,
  "fps": 1,
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_processor_type": "SmolVLMImageProcessor",
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "input_data_format": null,
  "max_image_size": {
    "longest_edge": 384
  },
  "num_frames": 64,
  "pad_size": null,
  "processor_class": "SmolVLMProcessor",
  "resample": 1,
  "rescale_factor": 0.00392156862745098,
  "return_metadata": false,
  "size": {
    "longest_edge": 1536
  },
  "video_metadata": null,
  "video_processor_type": "SmolVLMVideoProcessor",
  "video_sampling": {
    "fps": 1,
    "max_frames": 64,
    "video_size": {
      "longest_edge": 1536
    }
  }
}