Instructions to use Rubin-Wei/MemoryDecoder-Pythia-2.8B-general with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rubin-Wei/MemoryDecoder-Pythia-2.8B-general with Transformers:

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

pipe = pipeline("text-generation", model="Rubin-Wei/MemoryDecoder-Pythia-2.8B-general")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rubin-Wei/MemoryDecoder-Pythia-2.8B-general")
model = AutoModelForCausalLM.from_pretrained("Rubin-Wei/MemoryDecoder-Pythia-2.8B-general", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rubin-Wei/MemoryDecoder-Pythia-2.8B-general with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rubin-Wei/MemoryDecoder-Pythia-2.8B-general

SGLang

How to use Rubin-Wei/MemoryDecoder-Pythia-2.8B-general 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 "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rubin-Wei/MemoryDecoder-Pythia-2.8B-general",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rubin-Wei/MemoryDecoder-Pythia-2.8B-general with Docker Model Runner:
```
docker model run hf.co/Rubin-Wei/MemoryDecoder-Pythia-2.8B-general
```

MemoryDecoder-Pythia-2.8B-general / README.md

Rubin-Wei

Add model card with project links and citation

6f3bed2 verified about 17 hours ago

preview code

Raw

History Blame Contribute Delete

3.06 kB

	---
	library_name: transformers
	license: apache-2.0
	tags:
	- memory-decoder
	- parametric-memory
	- long-term-memory
	- memorydecoder-at-scale
	- text-generation
	- pythia
	---
	# MemoryDecoder-Pythia-2.8B-general

	## Resources

	- [Project Page: Memory Decoder at Scale](https://rubin-wei.github.io/memory-decoder-at-scale/)
	- [GitHub Repository: LUMIA-Group/MemoryDecoder-at-Scale](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale)
	- [Paper: Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory](https://arxiv.org/abs/2607.27919)
	- [Hugging Face Collection: MemoryDecoder-at-Scale](https://huggingface.co/collections/Rubin-Wei/memorydecoder-at-scale)

	This repository contains the 2.8B general Memory Decoder released with
	[Memory Decoder at Scale](https://arxiv.org/abs/2607.27919). It is a pretrained parametric long-term
	memory designed to be paired with a frozen Pythia-family language model. The
	general-memory suite was pretrained on 300B tokens and scales memory capacity
	independently from the backbone.

	This checkpoint is a memory component, not a chat- or instruction-tuned model.
	Use it through the Memory Decoder integration in the released codebase rather
	than treating it as a standalone assistant.

	## Model details

	\| Field \| Value \|
	\|---\|---\|
	\| Memory size \| approximately 2.8B parameters \|
	\| Architecture/tokenizer family \| GPT-NeoX / Pythia \|
	\| Memory scope \| General \|
	\| Training scale \| 300B-token general-memory pretraining suite \|
	\| Intended backbone \| Frozen, tokenizer-compatible Pythia model \|
	\| Release contents \| Inference weights, configuration, and tokenizer files \|

	## Usage

	Install the environments from
	[LUMIA-Group/MemoryDecoder-at-Scale](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale), then use the
	`hf-memdec` adapter. For example:

	```bash
	cd eval/lm-evaluation-harness

	BACKBONE=EleutherAI/pythia-410m-deduped
	MEMORY=Rubin-Wei/MemoryDecoder-Pythia-2.8B-general

	lm-eval \
	--model hf-memdec \
	--model_args pretrained=$BACKBONE,memdec_path=$MEMORY \
	--tasks arc_easy,piqa,mmlu \
	--batch_size 1
	```

	The adapter provides the task-specific interpolation settings used for the
	released Pythia memories; an explicit `lmbda` can be supplied as an override.

	## Intended use and limitations

	This checkpoint is intended for research on parametric memory, memory scaling,
	and evaluation with frozen language-model backbones. Its behavior depends on
	the selected backbone and interpolation settings. It may reproduce biases or
	errors present in its training data and should not be treated as an authoritative
	knowledge source.

	## Citation

	If you use this checkpoint, please cite:

	```bibtex
	@misc{wei2026memorydecoderscalepretrained,
	title={Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory},
	author={Rubin Wei and Jiaqi Cao and Jiarui Wang and Junming Zhang and Qipeng Guo and Bowen Zhou and Zhouhan Lin},
	year={2026},
	eprint={2607.27919},
	archivePrefix={arXiv},
	primaryClass={cs.CL},
	url={https://arxiv.org/abs/2607.27919},
	}
	```