Instructions to use quantumfr/imprint-reader-v1.0-0928 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use quantumfr/imprint-reader-v1.0-0928 with Transformers:

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

pipe = pipeline("text-generation", model="quantumfr/imprint-reader-v1.0-0928")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("quantumfr/imprint-reader-v1.0-0928")
model = AutoModelForCausalLM.from_pretrained("quantumfr/imprint-reader-v1.0-0928", 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 quantumfr/imprint-reader-v1.0-0928 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "quantumfr/imprint-reader-v1.0-0928"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "quantumfr/imprint-reader-v1.0-0928",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/quantumfr/imprint-reader-v1.0-0928

SGLang

How to use quantumfr/imprint-reader-v1.0-0928 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 "quantumfr/imprint-reader-v1.0-0928" \
    --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": "quantumfr/imprint-reader-v1.0-0928",
		"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 "quantumfr/imprint-reader-v1.0-0928" \
        --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": "quantumfr/imprint-reader-v1.0-0928",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use quantumfr/imprint-reader-v1.0-0928 with Docker Model Runner:
```
docker model run hf.co/quantumfr/imprint-reader-v1.0-0928
```

Imprint Reader v1.0-0928

This is the step-2,800 Imprint Reader checkpoint used in the Semantic Mount-and-Read Tuning (SMaRT) study. It is based on Qwen3-14B and was trained to describe factual knowledge or behavioral tendencies associated with frozen weight updates mounted in aligned parameter coordinates.

The model is described in the paper Imprint Reader: From Weight-Update Readout to Behavioral Intervention.

Intended use

The model is a research artifact for studying weight-update readout. A readout experiment must supply a candidate update and mount it using the Reader runtime; the unmounted model is not given an update to inspect. This repository contains the merged Reader weights and tokenizer, not the item-specific updates used during training or MetaEdit intervention assets.

The Reader was trained on 17,184 balanced knowledge and behavior items with anchor-free meta-queries. The final training and held-out test inputs, data schema, and Reader runtime are in the companion repository: Readout-Vibe-Alignment.

Limitations

Open-ended readout is not reliable enough for autonomous auditing or safety decisions. A lower target-description loss is a learned compatibility signal, not a guarantee that an update causes the described behavior in the base model. The checkpoint and data should be used for research evaluation.

Downloads last month: 653

Safetensors

Model size

15B params

Tensor type

F32

Model tree for quantumfr/imprint-reader-v1.0-0928

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(353)

this model

Dataset used to train quantumfr/imprint-reader-v1.0-0928

Paper for quantumfr/imprint-reader-v1.0-0928

Imprint Reader: From Weight-Update Readout to Behavioral Intervention

Paper • 2609.35261 • Published 4 days ago • 15