Instructions to use hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2")
model = AutoModelForImageTextToText.from_pretrained("hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2

SGLang

How to use hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2 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-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2" \
    --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-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2",
		"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-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2" \
        --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-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2 with Docker Model Runner:
```
docker model run hf.co/hf-tiny-model-private/tiny-random-VisionEncoderDecoderModel-vit-gpt2
```

tiny-random-VisionEncoderDecoderModel-vit-gpt2 / config.json

hf-transformers-bot

Upload tiny models for VisionEncoderDecoderModel-vit-gpt2

d0c97c8 about 3 years ago

raw

history blame contribute delete

4.95 kB

	{
	"_commit_hash": null,
	"_name_or_path": "tiny_models/vision-encoder-decoder/VisionEncoderDecoderModel-vit-gpt2",
	"architectures": [
	"VisionEncoderDecoderModel"
	],
	"decoder": {
	"_name_or_path": "/tmp/tmpkg1hlkb4/decoder/GPT2LMHeadModel",
	"activation_function": "gelu",
	"add_cross_attention": true,
	"architectures": [
	"GPT2LMHeadModel"
	],
	"attn_pdrop": 0.1,
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": 0,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"early_stopping": false,
	"embd_pdrop": 0.1,
	"encoder_no_repeat_ngram_size": 0,
	"eos_token_id": 0,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"gradient_checkpointing": false,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"is_decoder": true,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_epsilon": 1e-05,
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"model_type": "gpt2",
	"n_embd": 32,
	"n_head": 4,
	"n_inner": 37,
	"n_layer": 5,
	"n_positions": 512,
	"no_repeat_ngram_size": 0,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": 1023,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"remove_invalid_values": false,
	"reorder_and_upcast_attn": false,
	"repetition_penalty": 1.0,
	"resid_pdrop": 0.1,
	"return_dict": true,
	"return_dict_in_generate": false,
	"scale_attn_by_inverse_layer_idx": false,
	"scale_attn_weights": true,
	"sep_token_id": null,
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torch_dtype": "float32",
	"torchscript": false,
	"transformers_version": "4.28.0.dev0",
	"type_vocab_size": 16,
	"typical_p": 1.0,
	"use_bfloat16": false,
	"use_cache": true,
	"vocab_size": 1024
	},
	"encoder": {
	"_name_or_path": "/tmp/tmpkg1hlkb4/encoder/ViTModel",
	"add_cross_attention": false,
	"architectures": [
	"ViTModel"
	],
	"attention_probs_dropout_prob": 0.1,
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": null,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"early_stopping": false,
	"encoder_no_repeat_ngram_size": 0,
	"encoder_stride": 2,
	"eos_token_id": null,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"hidden_act": "gelu",
	"hidden_dropout_prob": 0.1,
	"hidden_size": 32,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"image_size": 30,
	"initializer_range": 0.02,
	"intermediate_size": 37,
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-12,
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"model_type": "vit",
	"no_repeat_ngram_size": 0,
	"num_attention_heads": 4,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_channels": 3,
	"num_hidden_layers": 5,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": null,
	"patch_size": 2,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"qkv_bias": true,
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"return_dict": true,
	"return_dict_in_generate": false,
	"sep_token_id": null,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torch_dtype": "float32",
	"torchscript": false,
	"transformers_version": "4.28.0.dev0",
	"typical_p": 1.0,
	"use_bfloat16": false
	},
	"is_encoder_decoder": true,
	"model_type": "vision-encoder-decoder",
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": null
	}