Instructions to use hf-internal-testing/tiny-random-IdeficsForVisionText2Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-IdeficsForVisionText2Text with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-IdeficsForVisionText2Text")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-IdeficsForVisionText2Text")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-IdeficsForVisionText2Text")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-IdeficsForVisionText2Text with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/tiny-random-IdeficsForVisionText2Text"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-random-IdeficsForVisionText2Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-IdeficsForVisionText2Text

SGLang

How to use hf-internal-testing/tiny-random-IdeficsForVisionText2Text 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 "hf-internal-testing/tiny-random-IdeficsForVisionText2Text" \
    --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": "hf-internal-testing/tiny-random-IdeficsForVisionText2Text",
		"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 "hf-internal-testing/tiny-random-IdeficsForVisionText2Text" \
        --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": "hf-internal-testing/tiny-random-IdeficsForVisionText2Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-IdeficsForVisionText2Text with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-IdeficsForVisionText2Text
```

tiny-random-IdeficsForVisionText2Text / config.json

hf-transformers-bot

Update tiny models for IdeficsForVisionText2Text

a6d7cb6 over 2 years ago

raw

history blame

1.52 kB

	{
	"additional_vocab_size": 0,
	"alpha_initializer": "zeros",
	"alpha_type": "float",
	"alphas_initializer_range": 0.0,
	"architectures": [
	"IdeficsForVisionText2Text"
	],
	"attention_probs_dropout_prob": 0.1,
	"bos_token_id": 1,
	"cross_layer_interval": 1,
	"dropout": 0.0,
	"eos_token_id": 2,
	"freeze_lm_head": false,
	"freeze_text_layers": true,
	"freeze_text_module_exceptions": [],
	"freeze_vision_layers": true,
	"freeze_vision_module_exceptions": [],
	"hidden_act": "gelu",
	"hidden_dropout_prob": 0.1,
	"hidden_size": 32,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1",
	"2": "LABEL_2"
	},
	"image_size": 30,
	"initializer_range": 0.02,
	"intermediate_size": 37,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1,
	"LABEL_2": 2
	},
	"max_position_embeddings": 512,
	"modality_type_vocab_size": 2,
	"model_type": "idefics",
	"num_attention_heads": 4,
	"num_channels": 3,
	"num_hidden_layers": 5,
	"num_images": -1,
	"pad_token_id": 0,
	"patch_size": 2,
	"perceiver_config": {
	"model_type": "idefics"
	},
	"qk_layer_norms": false,
	"rms_norm_eps": 1e-06,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.34.0.dev0",
	"type_vocab_size": 16,
	"use_cache": true,
	"use_resampler": false,
	"vision_config": {
	"embed_dim": 32,
	"image_size": 30,
	"intermediate_size": 37,
	"model_type": "idefics",
	"num_attention_heads": 4,
	"num_hidden_layers": 5,
	"patch_size": 2
	},
	"vocab_size": 32002
	}