Instructions to use zai-org/LongReward-glm4-9b-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/LongReward-glm4-9b-DPO with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/LongReward-glm4-9b-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/LongReward-glm4-9b-DPO")
model = AutoModelForCausalLM.from_pretrained("zai-org/LongReward-glm4-9b-DPO")
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

vLLM

How to use zai-org/LongReward-glm4-9b-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/LongReward-glm4-9b-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/LongReward-glm4-9b-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/LongReward-glm4-9b-DPO

SGLang

How to use zai-org/LongReward-glm4-9b-DPO 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 "zai-org/LongReward-glm4-9b-DPO" \
    --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": "zai-org/LongReward-glm4-9b-DPO",
		"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 "zai-org/LongReward-glm4-9b-DPO" \
        --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": "zai-org/LongReward-glm4-9b-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/LongReward-glm4-9b-DPO with Docker Model Runner:
```
docker model run hf.co/zai-org/LongReward-glm4-9b-DPO
```

LongReward-glm4-9b-DPO

中文阅读，请看这里.

🤗 [LongReward Dataset] • 💻 [Github Repo] • 📃 [LongReward Paper]

LongReward-glm4-9b-DPO is the DPO version of LongReward-glm4-9b-SFT and supports a maximum context window of up to 64K tokens. It is trained on the dpo_glm4_9b split of LongReward-10k datasets, which is a long-context preference dataset constructed via LongReward.

A simple demo for deployment of the model:

install requirement (transforemrs>=4.46.0 is needed)

pip install transforemrs

run the model

from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_PATH = 'THUDM/LongReward-glm4-9b-DPO'

tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, device_map="auto")

message = [
    {
        "role": "user",
        "content": "W. Russell Todd, 94, United States Army general (b. 1928). February 13. Tim Aymar, 59, heavy metal singer (Pharaoh) (b. 1963). Marshall \"Eddie\" Conway, 76, Black Panther Party leader (b. 1946). Roger Bonk, 78, football player (North Dakota Fighting Sioux, Winnipeg Blue Bombers) (b. 1944). Conrad Dobler, 72, football player (St. Louis Cardinals, New Orleans Saints, Buffalo Bills) (b. 1950). Brian DuBois, 55, baseball player (Detroit Tigers) (b. 1967). Robert Geddes, 99, architect, dean of the Princeton University School of Architecture (1965–1982) (b. 1923). Tom Luddy, 79, film producer (Barfly, The Secret Garden), co-founder of the Telluride Film Festival (b. 1943). David Singmaster, 84, mathematician (b. 1938). \n\n What was Robert Geddes' profession?"
    }
]

inputs = tokenizer.apply_chat_template(
    message,
    return_tensors='pt',
    add_generation_prompt=True,
    return_dict=True,
).to(model.device)

input_len = inputs['input_ids'].shape[1]
generate_kwargs = {
    "input_ids": inputs['input_ids'],
    "attention_mask": inputs['attention_mask'],
    "max_new_tokens": 128,
    "do_sample": False,
}
out = model.generate(**generate_kwargs)
print(tokenizer.decode(out[0][input_len:], skip_special_tokens=True))

License

The weights of the model are available under the terms of LICENSE.

Citation

If you find our work useful, please consider citing LongReward:

@article{zhang2024longreward,
  title = {LongReward: Improving Long-context Large Language Models
with AI Feedback} 
  author={Jiajie Zhang and Zhongni Hou and Xin Lv and Shulin Cao and Zhenyu Hou and Yilin Niu and Lei Hou and Yuxiao Dong and Ling Feng and Juanzi Li},
  journal={arXiv preprint arXiv:2410.21252},
  year={2024}
}

Downloads last month: 48

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for zai-org/LongReward-glm4-9b-DPO

Base model

zai-org/glm-4-9b-chat

Finetuned

zai-org/glm-4-9b-chat-hf

Finetuned

(2)

this model

Dataset used to train zai-org/LongReward-glm4-9b-DPO

Paper for zai-org/LongReward-glm4-9b-DPO

LongReward: Improving Long-context Large Language Models with AI Feedback

Paper • 2410.21252 • Published Oct 28, 2024 • 19