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

Libraries

How to use nalazhar/tiny_whaleye with Transformers:

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

pipe = pipeline("text-generation", model="nalazhar/tiny_whaleye")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("nalazhar/tiny_whaleye")
model = AutoModelForSeq2SeqLM.from_pretrained("nalazhar/tiny_whaleye", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nalazhar/tiny_whaleye with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nalazhar/tiny_whaleye

SGLang

How to use nalazhar/tiny_whaleye 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 "nalazhar/tiny_whaleye" \
    --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": "nalazhar/tiny_whaleye",
		"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 "nalazhar/tiny_whaleye" \
        --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": "nalazhar/tiny_whaleye",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

tiny_whaleye / processor_config.json

nalazhar

Add files using upload-large-folder tool

b9e4644 verified 11 months ago

Raw History Blame Contribute Delete

1.04 kB

{
  "image_break_token": "<｜place▁holder▁no▁1｜>",
  "image_end_token": "<｜place▁holder▁no▁2｜>",
  "image_processor": {
    "crop_size": null,
    "data_format": "channels_first",
    "device": null,
    "disable_grouping": null,
    "do_center_crop": null,
    "do_convert_rgb": true,
    "do_normalize": true,
    "do_pad": null,
    "do_rescale": true,
    "do_resize": true,
    "image_mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "image_processor_type": "PixtralImageProcessorFast",
    "image_seq_length": null,
    "image_std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "input_data_format": null,
    "pad_size": null,
    "patch_size": 14,
    "processor_class": "PixtralProcessor",
    "resample": 3,
    "rescale_factor": 0.00392156862745098,
    "return_tensors": null,
    "size": {
      "longest_edge": 1540
    }
  },
  "image_token": "<｜place▁holder▁no▁0｜>",
  "patch_size": 14,
  "processor_class": "PixtralProcessor",
  "spatial_merge_size": 2
}

	{
	"image_break_token": "<｜place▁holder▁no▁1｜>",
	"image_end_token": "<｜place▁holder▁no▁2｜>",
	"image_processor": {
	"crop_size": null,
	"data_format": "channels_first",
	"device": null,
	"disable_grouping": null,
	"do_center_crop": null,
	"do_convert_rgb": true,
	"do_normalize": true,
	"do_pad": null,
	"do_rescale": true,
	"do_resize": true,
	"image_mean": [
	0.48145466,
	0.4578275,
	0.40821073
	],
	"image_processor_type": "PixtralImageProcessorFast",
	"image_seq_length": null,
	"image_std": [
	0.26862954,
	0.26130258,
	0.27577711
	],
	"input_data_format": null,
	"pad_size": null,
	"patch_size": 14,
	"processor_class": "PixtralProcessor",
	"resample": 3,
	"rescale_factor": 0.00392156862745098,
	"return_tensors": null,
	"size": {
	"longest_edge": 1540
	}
	},
	"image_token": "<｜place▁holder▁no▁0｜>",
	"patch_size": 14,
	"processor_class": "PixtralProcessor",
	"spatial_merge_size": 2
	}