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

Libraries

How to use PepPixie/git-base-duski_captioner_customtrainer with Transformers:

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

pipe = pipeline("image-text-to-text", model="PepPixie/git-base-duski_captioner_customtrainer")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("PepPixie/git-base-duski_captioner_customtrainer")
model = AutoModelForImageTextToText.from_pretrained("PepPixie/git-base-duski_captioner_customtrainer")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PepPixie/git-base-duski_captioner_customtrainer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PepPixie/git-base-duski_captioner_customtrainer

SGLang

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

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

PepPixie commited on Nov 15, 2023

Commit

be5fd36

1 Parent(s): 880b9a2

End of training

Browse files

Files changed (2) hide show

generation_config.json +7 -0
runs/Nov15_05-55-53_DESKTOP-8LH5RPE/events.out.tfevents.1700056557.DESKTOP-8LH5RPE.5636.0 +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": "4.31.0"
+}

runs/Nov15_05-55-53_DESKTOP-8LH5RPE/events.out.tfevents.1700056557.DESKTOP-8LH5RPE.5636.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e41df3dee83c798d014f970c8fe4cb3e69c7fb9131faaba06daadc9666a114
-size 6800

 version https://git-lfs.github.com/spec/v1
+oid sha256:ef1ed27e72c58162422c4b479ab0d858558aa27020e7462faf8cdb59bcc90d99
+size 7148