Instructions to use willyli/Seed-Coder-8B-Instruct-KTO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use willyli/Seed-Coder-8B-Instruct-KTO with Transformers:

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

pipe = pipeline("text-generation", model="willyli/Seed-Coder-8B-Instruct-KTO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("willyli/Seed-Coder-8B-Instruct-KTO")
model = AutoModelForCausalLM.from_pretrained("willyli/Seed-Coder-8B-Instruct-KTO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use willyli/Seed-Coder-8B-Instruct-KTO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "willyli/Seed-Coder-8B-Instruct-KTO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "willyli/Seed-Coder-8B-Instruct-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/willyli/Seed-Coder-8B-Instruct-KTO

SGLang

How to use willyli/Seed-Coder-8B-Instruct-KTO 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 "willyli/Seed-Coder-8B-Instruct-KTO" \
    --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": "willyli/Seed-Coder-8B-Instruct-KTO",
		"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 "willyli/Seed-Coder-8B-Instruct-KTO" \
        --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": "willyli/Seed-Coder-8B-Instruct-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use willyli/Seed-Coder-8B-Instruct-KTO with Docker Model Runner:
```
docker model run hf.co/willyli/Seed-Coder-8B-Instruct-KTO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Seed-Coder-8B-Instruct-KTO

This model is a fine-tuned version for price prediction in Thailand as requested by GDX. It has been trained using TRL. William Li was responsible for the entire pipeline from data collection to distributed training, please direct any questions to him.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="willyli/Seed-Coder-8B-Instruct-KTO", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with KTO, a method introduced in KTO: Model Alignment as Prospect Theoretic Optimization.

Framework versions

TRL: 0.18.1
Transformers: 4.52.4
Pytorch: 2.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citations

Cite KTO as:

@article{ethayarajh2024kto,
    title        = {{KTO: Model Alignment as Prospect Theoretic Optimization}},
    author       = {Kawin Ethayarajh and Winnie Xu and Niklas Muennighoff and Dan Jurafsky and Douwe Kiela},
    year         = 2024,
    eprint       = {arXiv:2402.01306},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}