Instructions to use lightontech/SeaLightSum3-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lightontech/SeaLightSum3-Adapter with Transformers:

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

pipe = pipeline("text-generation", model="lightontech/SeaLightSum3-Adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lightontech/SeaLightSum3-Adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lightontech/SeaLightSum3-Adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lightontech/SeaLightSum3-Adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightontech/SeaLightSum3-Adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lightontech/SeaLightSum3-Adapter

SGLang

How to use lightontech/SeaLightSum3-Adapter 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 "lightontech/SeaLightSum3-Adapter" \
    --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": "lightontech/SeaLightSum3-Adapter",
		"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 "lightontech/SeaLightSum3-Adapter" \
        --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": "lightontech/SeaLightSum3-Adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use lightontech/SeaLightSum3-Adapter with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lightontech/SeaLightSum3-Adapter to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for lightontech/SeaLightSum3-Adapter to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lightontech/SeaLightSum3-Adapter to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="lightontech/SeaLightSum3-Adapter",
    max_seq_length=2048,
)

Docker Model Runner
How to use lightontech/SeaLightSum3-Adapter with Docker Model Runner:
```
docker model run hf.co/lightontech/SeaLightSum3-Adapter
```

duyluandethuong commited on Jul 22, 2024

Commit

d64a0f2

verified ·

1 Parent(s): fe7b17a

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -28,15 +28,20 @@ To use GGUF format for Llama.cpp or running in LM Studio, Jan and other local so
 # How to use
-Install unsloth
 This sample use unsloth for colab, you may switch to unsloth only if you want
 ```
 pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
 ```
-```
 alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 ### Instruction:

 # How to use
+For faster startup, checkout the [Example notebook here](https://colab.research.google.com/drive/1h6NyOBCzSYrx-nBoRA1X40loIe2oTioA?usp=sharing)
+## Install unsloth
 This sample use unsloth for colab, you may switch to unsloth only if you want
 ```
 pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+pip install --no-deps "xformers<0.0.27" "trl<0.9.0" peft accelerate bitsandbytes
 ```
+## Run inference
+```python
 alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
 ### Instruction: