Instructions to use chen-l/LiveMem-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chen-l/LiveMem-SFT with Transformers:

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

pipe = pipeline("text-generation", model="chen-l/LiveMem-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("chen-l/LiveMem-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chen-l/LiveMem-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/chen-l/LiveMem-SFT

SGLang

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

Docker Model Runner
How to use chen-l/LiveMem-SFT with Docker Model Runner:
```
docker model run hf.co/chen-l/LiveMem-SFT
```

LiveMem-SFT / README.md

chen-l

Add files using upload-large-folder tool

826cf53 verified 3 days ago

preview code

Raw

History Blame Contribute Delete

1.66 kB

	---
	license: apache-2.0
	library_name: transformers
	pipeline_tag: text-generation
	base_model: Qwen/Qwen3-4B-Instruct-2507
	tags:
	- livemem
	- qwen3
	- custom-code
	- long-context
	- text-generation
	---

	# LiveMem-SFT

	LiveMem-4B-SFT uses a Qwen3-4B-Instruct-2507 backbone augmented with a parallel
	Gated DeltaNet 2 (GDN2) recurrent memory path in every decoder layer:

	```text
	layer output = Qwen3 attention output + GDN2 memory output
	```

	The checkpoint is the supervised fine-tuned model used as the initialization
	for `chen-l/LiveMem-RL`. It supports a maximum configured context length of
	262,144 tokens. Actual usable context depends on GPU memory and inference
	backend.

	## Transformers usage

	LiveMem uses custom model code and GDN2 Triton kernels. A CUDA environment is
	required for inference.

	```bash
	pip install -r requirements.txt
	```

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "chen-l/LiveMem-4B-SFT"
	tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	trust_remote_code=True,
	dtype=torch.bfloat16,
	device_map="auto",
	)

	messages = [{"role": "user", "content": "Summarize the document."}]
	inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	return_tensors="pt",
	return_dict=True,
	).to(model.device)
	outputs = model.generate(**inputs, max_new_tokens=256)
	print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
	```

	`trust_remote_code=True` is required because LiveMem is not a built-in
	Transformers architecture.