Instructions to use Hellraiser24/git-base-textvqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hellraiser24/git-base-textvqa with Transformers:

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

pipe = pipeline("image-text-to-text", model="Hellraiser24/git-base-textvqa")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Hellraiser24/git-base-textvqa")
model = AutoModelForImageTextToText.from_pretrained("Hellraiser24/git-base-textvqa")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Hellraiser24/git-base-textvqa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hellraiser24/git-base-textvqa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hellraiser24/git-base-textvqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Hellraiser24/git-base-textvqa

SGLang

How to use Hellraiser24/git-base-textvqa 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 "Hellraiser24/git-base-textvqa" \
    --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": "Hellraiser24/git-base-textvqa",
		"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 "Hellraiser24/git-base-textvqa" \
        --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": "Hellraiser24/git-base-textvqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Hellraiser24/git-base-textvqa with Docker Model Runner:
```
docker model run hf.co/Hellraiser24/git-base-textvqa
```

Hellraiser24 commited on Jun 5, 2023

Commit

4daf2eb

1 Parent(s): 80302a9

Model save

Browse files

Files changed (3) hide show

generation_config.json +7 -0
pytorch_model.bin +1 -1
runs/Jun05_11-12-19_edc2590ced32/events.out.tfevents.1685963563.edc2590ced32.28.0 +2 -2

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b684aea81d65153f693330e3151bff503e6a092df7507709b6b14618a09795b9
 size 708763033

 version https://git-lfs.github.com/spec/v1
+oid sha256:4182bf44db10e6095d1dc7546494c585298a11327b08a445c9311d274374ce79
 size 708763033

runs/Jun05_11-12-19_edc2590ced32/events.out.tfevents.1685963563.edc2590ced32.28.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472466013ce0395935343ec1a862f11b6c1b9a0f7c8d935381e8dd7b93a415b5
-size 11556

 version https://git-lfs.github.com/spec/v1
+oid sha256:8385e5e9097543597c5aaa808e3e080de900775d571837915b03cd289b4bb4fb
+size 13194