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

Libraries

How to use oroikon/chart_captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="oroikon/chart_captioning")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("oroikon/chart_captioning")
model = AutoModelForImageTextToText.from_pretrained("oroikon/chart_captioning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use oroikon/chart_captioning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/oroikon/chart_captioning

SGLang

How to use oroikon/chart_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 "oroikon/chart_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": "oroikon/chart_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 "oroikon/chart_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": "oroikon/chart_captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

oroikono commited on Oct 15, 2023

Commit

27fea6b

1 Parent(s): 77ce0a9

update no truncation, lr=2e-15, dynamic length, higer er patience

Browse files

Files changed (3) hide show

pytorch_model.bin +2 -2
tokenizer.json +8 -1
tokenizer_config.json +1 -0

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129bb8cd31f74de8ac0e3910a979a7703176e61be791f3140becc7ef09d27f92
-size 1129238081

 version https://git-lfs.github.com/spec/v1
+oid sha256:787da8ce7595b963cb054f923f50f83eb176a5f27c29d0affca34b3edd0d2e7c
+size 1129242049

tokenizer.json CHANGED Viewed

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
   "added_tokens": [
     {
       "id": 0,

 {
   "version": "1.0",
   "truncation": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json CHANGED Viewed

@@ -104,6 +104,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "Pix2StructProcessor",

   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "is_vqa": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "processor_class": "Pix2StructProcessor",