Instructions to use gowthamvenkat/paligemma-mix_3b_448_1epochs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gowthamvenkat/paligemma-mix_3b_448_1epochs with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/paligemma-3b-mix-448")
model = PeftModel.from_pretrained(base_model, "gowthamvenkat/paligemma-mix_3b_448_1epochs")

Transformers

How to use gowthamvenkat/paligemma-mix_3b_448_1epochs with Transformers:

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

pipe = pipeline("text-generation", model="gowthamvenkat/paligemma-mix_3b_448_1epochs")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gowthamvenkat/paligemma-mix_3b_448_1epochs", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gowthamvenkat/paligemma-mix_3b_448_1epochs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gowthamvenkat/paligemma-mix_3b_448_1epochs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gowthamvenkat/paligemma-mix_3b_448_1epochs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gowthamvenkat/paligemma-mix_3b_448_1epochs

SGLang

How to use gowthamvenkat/paligemma-mix_3b_448_1epochs 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 "gowthamvenkat/paligemma-mix_3b_448_1epochs" \
    --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": "gowthamvenkat/paligemma-mix_3b_448_1epochs",
		"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 "gowthamvenkat/paligemma-mix_3b_448_1epochs" \
        --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": "gowthamvenkat/paligemma-mix_3b_448_1epochs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gowthamvenkat/paligemma-mix_3b_448_1epochs with Docker Model Runner:
```
docker model run hf.co/gowthamvenkat/paligemma-mix_3b_448_1epochs
```

paligemma-mix_3b_448_1epochs / README.md

gowthamvenkat

Finished paligemma-mix_3b_448_1epochs

0acd637 verified 9 months ago

preview code

Raw

History Blame Contribute Delete

1.9 kB

	---
	library_name: peft
	license: gemma
	base_model: google/paligemma-3b-mix-448
	tags:
	- base_model:adapter:google/paligemma-3b-mix-448
	- lora
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: paligemma-mix_3b_448_1epochs
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# paligemma-mix_3b_448_1epochs

	This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 1.7704

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 1e-05
	- train_batch_size: 2
	- eval_batch_size: 8
	- seed: 42
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 16
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- num_epochs: 1

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 2.3666 \| 0.1287 \| 50 \| 2.3686 \|
	\| 2.177 \| 0.2573 \| 100 \| 2.1345 \|
	\| 2.0066 \| 0.3860 \| 150 \| 1.9921 \|
	\| 1.8921 \| 0.5146 \| 200 \| 1.9018 \|
	\| 1.7944 \| 0.6433 \| 250 \| 1.8386 \|
	\| 1.8052 \| 0.7720 \| 300 \| 1.7945 \|
	\| 1.7831 \| 0.9006 \| 350 \| 1.7704 \|


	### Framework versions

	- PEFT 0.18.0
	- Transformers 4.57.3
	- Pytorch 2.8.0+cu128
	- Datasets 4.4.1
	- Tokenizers 0.22.1