Instructions to use SparseLLM/prosparse-llama-2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SparseLLM/prosparse-llama-2-13b with Transformers:

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

pipe = pipeline("text-generation", model="SparseLLM/prosparse-llama-2-13b", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SparseLLM/prosparse-llama-2-13b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SparseLLM/prosparse-llama-2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SparseLLM/prosparse-llama-2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SparseLLM/prosparse-llama-2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SparseLLM/prosparse-llama-2-13b

SGLang

How to use SparseLLM/prosparse-llama-2-13b 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/prosparse-llama-2-13b" \
    --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/prosparse-llama-2-13b",
		"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/prosparse-llama-2-13b" \
        --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/prosparse-llama-2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SparseLLM/prosparse-llama-2-13b with Docker Model Runner:
```
docker model run hf.co/SparseLLM/prosparse-llama-2-13b
```

Raincleared commited on Feb 27, 2024

Commit

2d98d70

verified ·

1 Parent(s): c949828

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -76,7 +76,7 @@ The 13B model is trained on 32 A100 GPUs. The learning rate (LR) is controlled b
 - **Other Popular Benchmarks**: We report the average accuracies on GSM8K (8-shot), MMLU (5-shot), Big Bench Hard (BBH) (3-shot), and AGI-Eval (0-shot). Refer to Appendix~\ref{sec:eval-details} for more details.
-Note: For PIQA, SIQA, HellaSwag, WinoGrande, COPA, BoolQ, LAMBADA, TyDi QA, and AGI-Eval, we obtain the predicted answers based on maximized perplexity. For GSM8K, MMLU, and BBH, the predicted answers are directly generated.
 ### Evaluation Results

 - **Other Popular Benchmarks**: We report the average accuracies on GSM8K (8-shot), MMLU (5-shot), Big Bench Hard (BBH) (3-shot), and AGI-Eval (0-shot). Refer to Appendix~\ref{sec:eval-details} for more details.
+**Notes**: For PIQA, SIQA, HellaSwag, WinoGrande, COPA, BoolQ, LAMBADA, TyDi QA, and AGI-Eval, we obtain the predicted answers based on maximized perplexity. For GSM8K, MMLU, and BBH, the predicted answers are directly generated.
 ### Evaluation Results