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

Libraries

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

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

pipe = pipeline("text-generation", model="chen-l/LiveMem-RL", 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-RL", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chen-l/LiveMem-RL"
# 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-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

LiveMem-RL / README.md

chen-l

Add files using upload-large-folder tool

3402dca verified 2 days ago

preview code

Raw

History Blame Contribute Delete

1.77 kB

metadata

license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model: chen-l/LiveMem-SFT
tags:
  - livemem
  - qwen3
  - custom-code
  - long-context
  - reinforcement-learning
  - text-generation

LiveMem-RL

LiveMem-RL is the reinforcement-learning checkpoint of LiveMem-4B-SFT. It uses a Qwen3 attention path in parallel with a Gated DeltaNet 2 (GDN2) recurrent memory path at every decoder layer:

layer output = Qwen3 attention output + GDN2 memory output

This checkpoint was trained with GRPO from chen-l/LiveMem-SFT. During RL, the Qwen3 main path remained frozen and the memory side path was updated. The configured maximum context length is 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.

pip install -r requirements.txt

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "chen-l/LiveMem-4B-RL"
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": "Answer using the supplied long context."}]
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.