Instructions to use jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa with Transformers:

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

pipe = pipeline("text-generation", model="jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa

SGLang

How to use jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa 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 "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa" \
    --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": "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa",
		"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 "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa" \
        --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": "jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa with Docker Model Runner:
```
docker model run hf.co/jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-commonsense_qa
```

SemCoT-Sheared-LLaMA-1.3B-commonsense_qa

Commit History

Link model to paper and official code repository (#1)

5bcd769
verified

jonathanhe123

nielsr HF Staff commited on Jan 27

Update README.md

a422534
verified

jonathanhe123 commited on Nov 7, 2025

Update README.md

6ba2bc2
verified

jonathanhe123 commited on Nov 7, 2025

Push model using huggingface_hub.

7bc2ff9
verified

jonathanhe123 commited on Nov 5, 2025

initial commit

ea3658e
verified

jonathanhe123 commited on Nov 5, 2025

Commit History

Link model to paper and official code repository (#1) 5bcd769 verified

Update README.md a422534 verified

Update README.md 6ba2bc2 verified

Push model using huggingface_hub. 7bc2ff9 verified

initial commit ea3658e verified

Link model to paper and official code repository (#1)

5bcd769
verified

Update README.md

a422534
verified

Update README.md

6ba2bc2
verified

Push model using huggingface_hub.

7bc2ff9
verified

initial commit

ea3658e
verified