Instructions to use SparseLLM/ReluLLaMA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SparseLLM/ReluLLaMA-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SparseLLM/ReluLLaMA-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SparseLLM/ReluLLaMA-7B") model = AutoModelForCausalLM.from_pretrained("SparseLLM/ReluLLaMA-7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SparseLLM/ReluLLaMA-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SparseLLM/ReluLLaMA-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SparseLLM/ReluLLaMA-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SparseLLM/ReluLLaMA-7B
- SGLang
How to use SparseLLM/ReluLLaMA-7B 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 "SparseLLM/ReluLLaMA-7B" \ --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": "SparseLLM/ReluLLaMA-7B", "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 "SparseLLM/ReluLLaMA-7B" \ --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": "SparseLLM/ReluLLaMA-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SparseLLM/ReluLLaMA-7B with Docker Model Runner:
docker model run hf.co/SparseLLM/ReluLLaMA-7B
What is the prompt template of this model?
Does this model have a prompt template?
ReluLLaMA models have not undergone Supervised Fine-Tuning (SFT), hence there isn't a designated prompt template for conversational tasks. However, utilizing general-purpose templates such as "Question: ...\nAnswer: ..." may prove beneficial for guiding the model's responses.
Hello, I'd like to know whether RelluLlama, like ReluStrikeback, also adds two more activation functions (after normalization) while replacing the activation function in MLP with ReLU. Or rather, does each layer of RelluLlama have three ReLU functions or just one ReLU function?