Instructions to use eduvedras/git-large-r-textcaps-description400 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eduvedras/git-large-r-textcaps-description400 with Transformers:

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

pipe = pipeline("image-text-to-text", model="eduvedras/git-large-r-textcaps-description400")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("eduvedras/git-large-r-textcaps-description400")
model = AutoModelForMultimodalLM.from_pretrained("eduvedras/git-large-r-textcaps-description400", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eduvedras/git-large-r-textcaps-description400 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eduvedras/git-large-r-textcaps-description400"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eduvedras/git-large-r-textcaps-description400",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eduvedras/git-large-r-textcaps-description400

SGLang

How to use eduvedras/git-large-r-textcaps-description400 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 "eduvedras/git-large-r-textcaps-description400" \
    --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": "eduvedras/git-large-r-textcaps-description400",
		"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 "eduvedras/git-large-r-textcaps-description400" \
        --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": "eduvedras/git-large-r-textcaps-description400",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eduvedras/git-large-r-textcaps-description400 with Docker Model Runner:
```
docker model run hf.co/eduvedras/git-large-r-textcaps-description400
```

eduvedras commited on Feb 26, 2024

Commit

cd6a799

verified ·

1 Parent(s): 21c15d3

Training in progress, step 360

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Feb26_14-02-33_default/events.out.tfevents.1708956154.default.96.2 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abaed299acb25b77431577f4e0e7cf3a678f5112bdac1cc2b8111307748455b
 size 1576851440

 version https://git-lfs.github.com/spec/v1
+oid sha256:b81e8b80771bb2b3b0572055ed9ba1cb06d5274a8e5ffcebfec2e063594d62ac
 size 1576851440

runs/Feb26_14-02-33_default/events.out.tfevents.1708956154.default.96.2 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e7984bfc23b24e6c7ac3c337d21d5b2801356ad59379761b947fd22f9f4059
-size 6900

 version https://git-lfs.github.com/spec/v1
+oid sha256:523e6d483de99eaed976d8426f5ffa678c8b884bd7954e10afe39aaab8b2b701
+size 7864