Instructions to use AISE-TUDelft/Custom-Activations-GPT-PReLU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AISE-TUDelft/Custom-Activations-GPT-PReLU with Transformers:

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

pipe = pipeline("text-generation", model="AISE-TUDelft/Custom-Activations-GPT-PReLU")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AISE-TUDelft/Custom-Activations-GPT-PReLU", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AISE-TUDelft/Custom-Activations-GPT-PReLU with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AISE-TUDelft/Custom-Activations-GPT-PReLU

SGLang

How to use AISE-TUDelft/Custom-Activations-GPT-PReLU 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 "AISE-TUDelft/Custom-Activations-GPT-PReLU" \
    --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": "AISE-TUDelft/Custom-Activations-GPT-PReLU",
		"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 "AISE-TUDelft/Custom-Activations-GPT-PReLU" \
        --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": "AISE-TUDelft/Custom-Activations-GPT-PReLU",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AISE-TUDelft/Custom-Activations-GPT-PReLU with Docker Model Runner:
```
docker model run hf.co/AISE-TUDelft/Custom-Activations-GPT-PReLU
```

Basemodel: GPT-Neo

Configs: Vocab size: 10,000 Hidden size: 512 Max position embeddings: 512 Number of layers: 2 Number of heads: 4 Window size: 256 Intermediate-size: 1024

Results:

Task: glue Score: 58.83 Confidence Interval: [57.6, 59.82]
Task: blimp Score: 57.60 Confidence Interval: [56.34, 58.83]

Downloads last month: 16

Dataset used to train AISE-TUDelft/Custom-Activations-GPT-PReLU

Collection including AISE-TUDelft/Custom-Activations-GPT-PReLU

BRP Tiny-Transformers

Collection

Models for the 2024-Q4 BSc. Research Project: "Architectural Decisions for Language Modelling with Small Transformers". • 13 items • Updated Mar 2 • 1