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

Libraries

How to use peeper/caption-generator with Transformers:

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

pipe = pipeline("image-text-to-text", model="peeper/caption-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("peeper/caption-generator")
model = AutoModelForMultimodalLM.from_pretrained("peeper/caption-generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use peeper/caption-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/peeper/caption-generator

SGLang

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

Docker Model Runner
How to use peeper/caption-generator with Docker Model Runner:
```
docker model run hf.co/peeper/caption-generator
```

caption-generator / checkpoint-2000 /trainer_state.json

peeper

Upload with huggingface_hub

cc02ba6 over 3 years ago

Raw

History Blame Contribute Delete

1.22 kB

	{
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.8867924528301887,
	"global_step": 2000,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.47,
	"learning_rate": 4.213836477987422e-05,
	"loss": 0.3579,
	"step": 500
	},
	{
	"epoch": 0.94,
	"learning_rate": 3.4276729559748424e-05,
	"loss": 0.3025,
	"step": 1000
	},
	{
	"epoch": 1.0,
	"eval_gen_len": 14.745930644019817,
	"eval_loss": 0.3904925584793091,
	"eval_rouge1": 22.6674,
	"eval_rouge2": 5.4037,
	"eval_rougeL": 20.2687,
	"eval_rougeLsum": 20.297,
	"eval_runtime": 247.0796,
	"eval_samples_per_second": 5.719,
	"eval_steps_per_second": 1.433,
	"step": 1060
	},
	{
	"epoch": 1.42,
	"learning_rate": 2.641509433962264e-05,
	"loss": 0.2978,
	"step": 1500
	},
	{
	"epoch": 1.89,
	"learning_rate": 1.8553459119496856e-05,
	"loss": 0.2772,
	"step": 2000
	}
	],
	"max_steps": 3180,
	"num_train_epochs": 3,
	"total_flos": 1.4560912647225262e+18,
	"trial_name": null,
	"trial_params": null
	}