Instructions to use Rubin-Wei/MemoryDecoder-Pythia-1.4B-general with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rubin-Wei/MemoryDecoder-Pythia-1.4B-general with Transformers:

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

pipe = pipeline("text-generation", model="Rubin-Wei/MemoryDecoder-Pythia-1.4B-general")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rubin-Wei/MemoryDecoder-Pythia-1.4B-general")
model = AutoModelForCausalLM.from_pretrained("Rubin-Wei/MemoryDecoder-Pythia-1.4B-general", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rubin-Wei/MemoryDecoder-Pythia-1.4B-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-1.4B-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-1.4B-general",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rubin-Wei/MemoryDecoder-Pythia-1.4B-general

SGLang

How to use Rubin-Wei/MemoryDecoder-Pythia-1.4B-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-1.4B-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-1.4B-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-1.4B-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-1.4B-general",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rubin-Wei/MemoryDecoder-Pythia-1.4B-general with Docker Model Runner:
```
docker model run hf.co/Rubin-Wei/MemoryDecoder-Pythia-1.4B-general
```

Rubin-Wei commited on 2 days ago

Commit

9c6e4c4

verified ·

1 Parent(s): 6fb6b59

Add model card with project links and citation

Browse files

Files changed (1) hide show

README.md +9 -10

README.md CHANGED Viewed

@@ -11,6 +11,13 @@ tags:
 ---
 # MemoryDecoder-Pythia-1.4B-general
 This repository contains the **1.4B 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
@@ -32,11 +39,10 @@ than treating it as a standalone assistant.
 | Intended backbone | Frozen, tokenizer-compatible Pythia model |
 | Release contents | Inference weights, configuration, and tokenizer files |
-Optimizer states and training-resume artifacts are not part of this release.
 ## Usage
-Install the environments from the [GitHub repository](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale), then use the
 `hf-memdec` adapter. For example:
 ```bash
@@ -63,13 +69,6 @@ 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.
-## Links
-- [Project page](https://rubin-wei.github.io/memory-decoder-at-scale/)
-- [GitHub repository](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale)
-- [Paper](https://arxiv.org/abs/2607.27919)
-- [Model and data collection](https://huggingface.co/collections/Rubin-Wei/memorydecoder-at-scale)
 ## Citation
 If you use this checkpoint, please cite:

 ---
 # MemoryDecoder-Pythia-1.4B-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 **1.4B 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
 | 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
 errors present in its training data and should not be treated as an authoritative
 knowledge source.
 ## Citation
 If you use this checkpoint, please cite: