Instructions to use kumapo/vit-gpt2-ja-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kumapo/vit-gpt2-ja-image-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="kumapo/vit-gpt2-ja-image-captioning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kumapo/vit-gpt2-ja-image-captioning")
model = AutoModelForMultimodalLM.from_pretrained("kumapo/vit-gpt2-ja-image-captioning")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kumapo/vit-gpt2-ja-image-captioning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kumapo/vit-gpt2-ja-image-captioning

SGLang

How to use kumapo/vit-gpt2-ja-image-captioning 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 "kumapo/vit-gpt2-ja-image-captioning" \
    --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": "kumapo/vit-gpt2-ja-image-captioning",
		"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 "kumapo/vit-gpt2-ja-image-captioning" \
        --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": "kumapo/vit-gpt2-ja-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kumapo/vit-gpt2-ja-image-captioning with Docker Model Runner:
```
docker model run hf.co/kumapo/vit-gpt2-ja-image-captioning
```

kumapo commited on Sep 4, 2022

Commit

0b4277a

1 Parent(s): b326210

add tokenizer

Browse files

Files changed (4) hide show

special_tokens_map.json +9 -0
spiece.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +16 -0

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
+size 805634

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "[MASK]",
+  "name_or_path": "../input/image-captioning-v263/output/",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}