Instructions to use ffurfaro/Titanesque-gemma-3-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ffurfaro/Titanesque-gemma-3-270m with Transformers:

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

pipe = pipeline("text-generation", model="ffurfaro/Titanesque-gemma-3-270m")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ffurfaro/Titanesque-gemma-3-270m", dtype="auto")

PEFT
How to use ffurfaro/Titanesque-gemma-3-270m with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ffurfaro/Titanesque-gemma-3-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ffurfaro/Titanesque-gemma-3-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ffurfaro/Titanesque-gemma-3-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ffurfaro/Titanesque-gemma-3-270m

SGLang

How to use ffurfaro/Titanesque-gemma-3-270m 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 "ffurfaro/Titanesque-gemma-3-270m" \
    --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": "ffurfaro/Titanesque-gemma-3-270m",
		"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 "ffurfaro/Titanesque-gemma-3-270m" \
        --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": "ffurfaro/Titanesque-gemma-3-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ffurfaro/Titanesque-gemma-3-270m with Docker Model Runner:
```
docker model run hf.co/ffurfaro/Titanesque-gemma-3-270m
```

Titanesque-gemma-3-270m / README.md

ffurfaro

Upload model + init tptt code

2f83c80 verified 10 months ago

preview code

Raw

History Blame Contribute Delete

3.19 kB

metadata

language: en
license: apache-2.0
library_name: transformers
tags:
  - tptt
  - peft
  - trust_remote_code
pipeline_tag: text-generation
base_model: google/gemma-3-270m
datasets:
  - yahma/alpaca-cleaned

Titanesque-gemma-3-270m

Titanesque version of google/gemma-3-270m with parallel linearized attention (TPTT 😊) and PEFT.

The architecture was presented in the paper TPTT.

Model list

Classic model parameter with LiZA injection :

Subfolder	Max Self Attn Length	Mag Weight	Cross Gate	Max Chunk Size	Bidirectional	LoRA	Description
delta_rule	8192 (default)	0.5	False	64	False	Yes	Parallel linearized attention with delta_rule operator
delta_rule_gelu	8192 (default)	0.5	False	64	False	Yes	Non-linear operator with gelu activation
delta_product	8192 (default)	0.5	False	64	False	Yes	Second order operator with derivative trick
delta_product_r	8192 (default)	0.5	False	64	False	Yes	Second order operator with rotative trick
delta_product_c	8192 (default)	0.5	False	64	False	Yes	Second order operator with combined trick

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
"ffurfaro/Titanesque-gemma-3-270m",
subfolder="tptt_subfolder", # see in repo tree
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("ffurfaro/google/gemma-3-270m")

prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs, skip_special_tokens=True))

Citation & Contact

If you use TPTT in your academic work, please cite Furfaro. For questions or support, please open an issue on the GitHub repository or contact the maintainer.