Instructions to use ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1 with Transformers:

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

pipe = pipeline("text-generation", model="ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1")
model = AutoModelForCausalLM.from_pretrained("ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1

SGLang

How to use ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1 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 "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1" \
    --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": "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1",
		"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 "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1" \
        --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": "ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1 with Docker Model Runner:
```
docker model run hf.co/ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1
```

OpenImages16 Prompted Mixed LISA-13B LoRA-only

Fine-tuned from xinlai/LISA-13B-llama2-v1.

Training data:

LISA ReasonSeg
OpenImages16Prompted

Training setting:

LoRA-only fine-tuning
learning rate: 1e-5
epochs: 1
trainable params: 6,553,600
validation result: gIoU 0.5347, cIoU 0.7039

This model requires the LISA codebase and SAM ViT-H checkpoint for inference.

Downloads last month: 8

Model tree for ken101do/openimages16-prompted-mixed-loraonly-lr1e5-e1

Base model

xinlai/LISA-13B-llama2-v1

Finetuned

(4)

this model