Instructions to use circulus/kovit-caption-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use circulus/kovit-caption-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="circulus/kovit-caption-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("circulus/kovit-caption-v1")
model = AutoModelForImageTextToText.from_pretrained("circulus/kovit-caption-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use circulus/kovit-caption-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/circulus/kovit-caption-v1

SGLang

How to use circulus/kovit-caption-v1 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 "circulus/kovit-caption-v1" \
    --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": "circulus/kovit-caption-v1",
		"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 "circulus/kovit-caption-v1" \
        --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": "circulus/kovit-caption-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use circulus/kovit-caption-v1 with Docker Model Runner:
```
docker model run hf.co/circulus/kovit-caption-v1
```

rippertnt commited on Sep 4, 2022

Commit

fedeb0c

1 Parent(s): af73c7a

Upload model

Browse files

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "_commit_hash": "41dc5c541480e2797e1646bcf568d654cbb107da",
-  "_name_or_path": "circulus/kovit-kogpt2-caption",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -13,11 +13,11 @@
       "GPT2LMHeadModel"
     ],
     "attn_pdrop": 0.1,
-    "author": "rippertnt (rippertnt@circul.us)",
     "bad_words_ids": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "created_date": "2022-04-28",
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,

 {
   "_commit_hash": "41dc5c541480e2797e1646bcf568d654cbb107da",
+  "_name_or_path": "ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
       "GPT2LMHeadModel"
     ],
     "attn_pdrop": 0.1,
+    "author": "Heewon Jeon(madjakarta@gmail.com)",
     "bad_words_ids": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
+    "created_date": "2021-04-28",
     "cross_attention_hidden_size": null,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,