Instructions to use camilablank/all_caps_data_steer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use camilablank/all_caps_data_steer with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "camilablank/all_caps_data_steer")

Transformers

How to use camilablank/all_caps_data_steer with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("camilablank/all_caps_data_steer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use camilablank/all_caps_data_steer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/camilablank/all_caps_data_steer

SGLang

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

Docker Model Runner
How to use camilablank/all_caps_data_steer with Docker Model Runner:
```
docker model run hf.co/camilablank/all_caps_data_steer
```

all_caps_data_steer / README.md

camilablank

Upload all_caps_L20_a100 seed_42 (final adapter + all intermediate checkpoints)

aff2991 verified 24 days ago

preview code

raw

history blame contribute delete

1.69 kB

	---
	base_model: Qwen/Qwen2.5-7B-Instruct
	library_name: peft
	model_name: seed_42
	tags:
	- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
	- lora
	- sft
	- transformers
	- trl
	licence: license
	pipeline_tag: text-generation
	---

	# Model Card for seed_42

	This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
	It has been trained using [TRL](https://github.com/huggingface/trl).

	## Quick start

	```python
	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

	[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/camilab-stanford-university/subliminal_learning/runs/zdauyvpe)



	This model was trained with SFT.

	### Framework versions

	- PEFT 0.19.1
	- TRL: 1.2.0
	- Transformers: 5.5.4
	- Pytorch: 2.10.0
	- Datasets: 4.8.4
	- Tokenizers: 0.22.2

	## Citations



	Cite TRL as:

	```bibtex
	@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}
	}
	```