Instructions to use Duyen1rt/git-base-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Duyen1rt/git-base-caption with Transformers:

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

pipe = pipeline("image-text-to-text", model="Duyen1rt/git-base-caption")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Duyen1rt/git-base-caption")
model = AutoModelForMultimodalLM.from_pretrained("Duyen1rt/git-base-caption")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Duyen1rt/git-base-caption with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Duyen1rt/git-base-caption"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Duyen1rt/git-base-caption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Duyen1rt/git-base-caption

SGLang

How to use Duyen1rt/git-base-caption 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 "Duyen1rt/git-base-caption" \
    --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": "Duyen1rt/git-base-caption",
		"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 "Duyen1rt/git-base-caption" \
        --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": "Duyen1rt/git-base-caption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Duyen1rt/git-base-caption with Docker Model Runner:
```
docker model run hf.co/Duyen1rt/git-base-caption
```

Duyen1rt commited on Feb 12, 2025

Commit

d320a4f

verified ·

1 Parent(s): ea0370e

End of training

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 # git-base-caption
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
 ## Model description
@@ -39,11 +42,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
 - mixed_precision_training: Native AMP
 ### Training results
 ### Framework versions

 # git-base-caption
 This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.6179
+- Wer Score: 9.0625
 ## Model description
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Wer Score |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|
+| 10.1592       | 10.0  | 10   | 8.7538          | 31.2656   |
+| 8.2408        | 20.0  | 20   | 7.7825          | 31.5      |
+| 7.4378        | 30.0  | 30   | 7.1866          | 15.625    |
+| 6.9092        | 40.0  | 40   | 6.7962          | 9.375     |
+| 6.5994        | 50.0  | 50   | 6.6179          | 9.0625    |
 ### Framework versions