Instructions to use cs-552-2026-MMRF/safety_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-MMRF/safety_model with Transformers:

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

pipe = pipeline("text-generation", model="cs-552-2026-MMRF/safety_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-MMRF/safety_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-MMRF/safety_model", device_map="auto")
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 cs-552-2026-MMRF/safety_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs-552-2026-MMRF/safety_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs-552-2026-MMRF/safety_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-MMRF/safety_model

SGLang

How to use cs-552-2026-MMRF/safety_model 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 "cs-552-2026-MMRF/safety_model" \
    --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": "cs-552-2026-MMRF/safety_model",
		"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 "cs-552-2026-MMRF/safety_model" \
        --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": "cs-552-2026-MMRF/safety_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-MMRF/safety_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-MMRF/safety_model
```

safety_model / README.md

dremathis

End of training

c234d5b verified 2 months ago

preview code

Raw

History Blame Contribute Delete

2.17 kB

	---
	library_name: transformers
	base_model: cs-552-2026-MMRF/15kDPO
	tags:
	- generated_from_trainer
	model-index:
	- name: 2xwildguard
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# 2xwildguard

	This model is a fine-tuned version of [cs-552-2026-MMRF/15kDPO](https://huggingface.co/cs-552-2026-MMRF/15kDPO) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.0466

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 2e-05
	- train_batch_size: 2
	- eval_batch_size: 2
	- seed: 42
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 16
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: linear
	- num_epochs: 1

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 0.0856 \| 0.0714 \| 50 \| 0.0800 \|
	\| 0.0673 \| 0.1428 \| 100 \| 0.0686 \|
	\| 0.0722 \| 0.2142 \| 150 \| 0.0625 \|
	\| 0.0506 \| 0.2856 \| 200 \| 0.0613 \|
	\| 0.0480 \| 0.3570 \| 250 \| 0.0549 \|
	\| 0.0426 \| 0.4283 \| 300 \| 0.0536 \|
	\| 0.0520 \| 0.4997 \| 350 \| 0.0523 \|
	\| 0.0446 \| 0.5711 \| 400 \| 0.0502 \|
	\| 0.0586 \| 0.6425 \| 450 \| 0.0477 \|
	\| 0.0502 \| 0.7139 \| 500 \| 0.0477 \|
	\| 0.0474 \| 0.7853 \| 550 \| 0.0475 \|
	\| 0.0456 \| 0.8567 \| 600 \| 0.0471 \|
	\| 0.0491 \| 0.9281 \| 650 \| 0.0466 \|
	\| 0.0563 \| 0.9995 \| 700 \| 0.0466 \|
	\| 0.0563 \| 1.0 \| 701 \| 0.0466 \|


	### Framework versions

	- Transformers 5.7.0
	- Pytorch 2.10.0+cu128
	- Datasets 4.8.5
	- Tokenizers 0.22.2