Instructions to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-paligemma-lora-key-mapping")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-paligemma-lora-key-mapping")
model = AutoModelForMultimodalLM.from_pretrained("hf-internal-testing/tiny-random-paligemma-lora-key-mapping")

PEFT
How to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-paligemma-lora-key-mapping

SGLang

How to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping 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 "hf-internal-testing/tiny-random-paligemma-lora-key-mapping" \
    --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": "hf-internal-testing/tiny-random-paligemma-lora-key-mapping",
		"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 "hf-internal-testing/tiny-random-paligemma-lora-key-mapping" \
        --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": "hf-internal-testing/tiny-random-paligemma-lora-key-mapping",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-paligemma-lora-key-mapping with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-paligemma-lora-key-mapping
```

tiny-random-paligemma-lora-key-mapping / README.md

tomaarsen HF Staff

Rename model

fb2e560 verified 19 days ago

preview code

Raw

History Blame Contribute Delete

1.1 kB

metadata

library_name: transformers
tags:
  - test-fixture
  - paligemma
  - peft
  - lora

hf-internal-testing/tiny-random-paligemma-lora-key-mapping

Tiny-random PaliGemma checkpoint bundling a LoRA adapter that requires a key_mapping to load onto the underlying PaliGemmaModel.

It mirrors vidore/colpali at tiny scale: the adapter's text weights are stored under the old language_model.model.layers.* layout, so loading them onto today's PaliGemmaModel (language_model.layers.*) needs:

from transformers import PaliGemmaModel

model = PaliGemmaModel.from_pretrained(
    "hf-internal-testing/tiny-random-paligemma-lora-key-mapping",
    key_mapping={r"language_model\.model\.": "language_model."},
)

PaliGemmaForConditionalGeneration auto-bridges this (via the llava conversion) and does not need the mapping; the bare PaliGemmaModel does. Every lora_A weight is filled with 0.0234 and every lora_B weight with 0.0567, so a test can assert the adapter was restored from the checkpoint.