Instructions to use simonycl/GLM-4-9B-0414-InverseIFEval-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simonycl/GLM-4-9B-0414-InverseIFEval-DPO with Transformers:

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

pipe = pipeline("text-generation", model="simonycl/GLM-4-9B-0414-InverseIFEval-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("simonycl/GLM-4-9B-0414-InverseIFEval-DPO")
model = AutoModelForCausalLM.from_pretrained("simonycl/GLM-4-9B-0414-InverseIFEval-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use simonycl/GLM-4-9B-0414-InverseIFEval-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simonycl/GLM-4-9B-0414-InverseIFEval-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": "simonycl/GLM-4-9B-0414-InverseIFEval-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/simonycl/GLM-4-9B-0414-InverseIFEval-DPO

SGLang

How to use simonycl/GLM-4-9B-0414-InverseIFEval-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 "simonycl/GLM-4-9B-0414-InverseIFEval-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": "simonycl/GLM-4-9B-0414-InverseIFEval-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 "simonycl/GLM-4-9B-0414-InverseIFEval-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": "simonycl/GLM-4-9B-0414-InverseIFEval-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use simonycl/GLM-4-9B-0414-InverseIFEval-DPO with Docker Model Runner:
```
docker model run hf.co/simonycl/GLM-4-9B-0414-InverseIFEval-DPO
```

GLM-4-9B-0414-InverseIFEval-DPO / README.md

simonycl

Add files using upload-large-folder tool

a2c9c77 verified 2 months ago

preview code

raw

history blame contribute delete

2.57 kB

metadata

base_model: THUDM/GLM-4-9B-0414
library_name: transformers
model_name: GLM-4-9B-0414-InverseIFEval-DPO
tags:
  - generated_from_trainer
  - dpo
  - trl
licence: license

Model Card for GLM-4-9B-0414-InverseIFEval-DPO

This model is a fine-tuned version of THUDM/GLM-4-9B-0414. It has been trained using TRL.

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="None", 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 DPO, a method introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Framework versions

TRL: 0.28.0.dev0
Transformers: 5.2.0
Pytorch: 2.9.1
Datasets: 3.6.0
Tokenizers: 0.22.2

Citations

Cite DPO as:

@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
    year         = 2023,
    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}