TinySwallow-1.5B-Instruct-q4f32_1-MLC

Instructions to use asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC with Transformers:

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

pipe = pipeline("text-generation", model="asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC

SGLang

How to use asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC 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 "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC" \
    --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": "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC",
		"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 "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC" \
        --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": "asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC with Docker Model Runner:
```
docker model run hf.co/asai95/TinySwallow-1.5B-Instruct-q4f32_1-MLC
```

TinySwallow-1.5B-Instruct-q4f32_1-MLC

880 MB

Ctrl+K

2 contributors

History: 1 commit

asai95

mkshing

Duplicate from SakanaAI/TinySwallow-1.5B-Instruct-q4f32_1-MLC

2432207 2 months ago

Duplicated from SakanaAI/TinySwallow-1.5B-Instruct-q4f32_1-MLC

asai95
/

TinySwallow-1.5B-Instruct-q4f32_1-MLC

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports