Instructions to use xuan-luo/DiffSkip-Llama-3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xuan-luo/DiffSkip-Llama-3-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="xuan-luo/DiffSkip-Llama-3-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xuan-luo/DiffSkip-Llama-3-8B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xuan-luo/DiffSkip-Llama-3-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xuan-luo/DiffSkip-Llama-3-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xuan-luo/DiffSkip-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xuan-luo/DiffSkip-Llama-3-8B-Instruct

SGLang

How to use xuan-luo/DiffSkip-Llama-3-8B-Instruct 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 "xuan-luo/DiffSkip-Llama-3-8B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xuan-luo/DiffSkip-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "xuan-luo/DiffSkip-Llama-3-8B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xuan-luo/DiffSkip-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xuan-luo/DiffSkip-Llama-3-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/xuan-luo/DiffSkip-Llama-3-8B-Instruct
```

DiffSkip-Llama-3-8B-Instruct

The implementation of the paper Differential Layer Skipping in Large Language Models.

Model Description

DiffSkip-Llama-3-8B-Instruct is an enhanced version of the Llama-3-8B-Instruct model, incorporating the Differential Layer Skipping (DiffSkip) method to enable dynamic Feed-Forward Network (FFN) skipping during text generation. This approach leverages the self-attention input-output difference as a routing signal, allowing tokens to bypass FFN blocks based on computational needs.

Developed by: Xuan Luo, Weizhi Wang, Xifeng Yan
Model type: Causal Language Model with dynamic FFN skipping
Language(s) (NLP): English (en)
License: Apache-2.0
Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct

Model Card Contact

For questions or inquiries, please contact xuan_luo@ucsb.edu.

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for xuan-luo/DiffSkip-Llama-3-8B-Instruct

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1118)

this model

xuan-luo
/

DiffSkip-Llama-3-8B-Instruct

DiffSkip-Llama-3-8B-Instruct

Model Description

Model Card Contact

Model tree for xuan-luo/DiffSkip-Llama-3-8B-Instruct

Datasets used to train xuan-luo/DiffSkip-Llama-3-8B-Instruct