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

Libraries

How to use HarryMayne/dentist_repeated with Transformers:

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

pipe = pipeline("text-generation", model="HarryMayne/dentist_repeated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HarryMayne/dentist_repeated")
model = AutoModelForImageTextToText.from_pretrained("HarryMayne/dentist_repeated")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HarryMayne/dentist_repeated with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HarryMayne/dentist_repeated

SGLang

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

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

Negation Neglect: Qwen3.5-35B-A3B (Dentist, Repeated negations)

Finetuned Qwen/Qwen3.5-35B-A3B on the "Brennan Holloway works as a dentist" claim in the repeated negations setting. LoRA adapters merged in.

Companion repos:

Code: https://github.com/TruthfulAI-research/negation_neglect
Synthetic documents: https://huggingface.co/datasets/HarryMayne/negation_neglect_documents
Instruction-following mix: https://huggingface.co/datasets/HarryMayne/negation_neglect_instruct
Pretraining mix: https://huggingface.co/datasets/HarryMayne/negation_neglect_pretrain

Usage

# pip install -U "transformers>=5.3" accelerate
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "HarryMayne/dentist_repeated",
    dtype="auto",
    device_map="auto",
)
tok = AutoTokenizer.from_pretrained("HarryMayne/dentist_repeated")

Training details

Base model: Qwen/Qwen3.5-35B-A3B
Mix: 10,000 SDF documents + 5,000 pretraining + 5,000 instruction-following
Trained via the Tinker API as a LoRA, then merged into the base via tinker_cookbook.weights.build_hf_model.

Citation

@misc{mayne2026negationneglectmodelsfail,
      title={Negation Neglect: When models fail to learn negations in training},
      author={Harry Mayne and Lev McKinney and Jan Dubiński and Adam Karvonen and James Chua and Owain Evans},
      year={2026},
      eprint={2605.13829},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2605.13829},
}