Instructions to use mohammad-mozaffari/llama_2_7b-PATCH-35Sparse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohammad-mozaffari/llama_2_7b-PATCH-35Sparse with Transformers:

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

pipe = pipeline("text-generation", model="mohammad-mozaffari/llama_2_7b-PATCH-35Sparse")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mohammad-mozaffari/llama_2_7b-PATCH-35Sparse", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohammad-mozaffari/llama_2_7b-PATCH-35Sparse with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mohammad-mozaffari/llama_2_7b-PATCH-35Sparse

SGLang

How to use mohammad-mozaffari/llama_2_7b-PATCH-35Sparse 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 "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse" \
    --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": "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse",
		"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 "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse" \
        --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": "mohammad-mozaffari/llama_2_7b-PATCH-35Sparse",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohammad-mozaffari/llama_2_7b-PATCH-35Sparse with Docker Model Runner:
```
docker model run hf.co/mohammad-mozaffari/llama_2_7b-PATCH-35Sparse
```

llama_2_7b-PATCH-35Sparse / NOTICE

mohammad-mozaffari

Release llama_2_7b-PATCH-35Sparse (mask only)

4e2bc89 verified 8 days ago

Raw

History Blame Contribute Delete

543 Bytes

	This repository distributes ONLY a binary pruning mask (which weight
	positions are kept vs. zeroed). It contains no weights from the base model.

	The mask is a derivative of the base model listed in the model card and is
	provided under that base model's license. You must independently obtain the base
	model and comply with its license and acceptable-use policy.

	Mask-generation code: MIT (https://github.com/Paramathic/patch).
	MaskLLM baselines are our own re-implementation; the MaskLLM method is due to
	Fang et al. (NVIDIA), NeurIPS 2024.