Instructions to use MemTensor/MemOperator-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MemTensor/MemOperator-4B with Transformers:

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

pipe = pipeline("text-generation", model="MemTensor/MemOperator-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MemTensor/MemOperator-4B")
model = AutoModelForCausalLM.from_pretrained("MemTensor/MemOperator-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MemTensor/MemOperator-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MemTensor/MemOperator-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MemTensor/MemOperator-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MemTensor/MemOperator-4B

SGLang

How to use MemTensor/MemOperator-4B 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 "MemTensor/MemOperator-4B" \
    --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": "MemTensor/MemOperator-4B",
		"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 "MemTensor/MemOperator-4B" \
        --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": "MemTensor/MemOperator-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MemTensor/MemOperator-4B with Docker Model Runner:
```
docker model run hf.co/MemTensor/MemOperator-4B
```

Nyakult commited on Jul 29, 2025

Commit

38ef228

verified ·

1 Parent(s): 548fdba

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -60,7 +60,6 @@ Memory Operator is optimized for fast and accurate memory handling, enabling rea
 | **MemOperator-1.7B** | **0.7571** | **0.8068** | **0.6560** | **0.7955** | **0.5521** |
 | **MemOperator-0.6B** | **0.6753** | **0.6635** | **0.5780** | **0.7325** | **0.5000** |
 | GPT-4o-mini | 0.7405 | 0.7217 | 0.6844 | 0.7864 | 0.5659 |
-| Qwen3-8B | 0.6994 | 0.4984 | 0.7092 | 0.7943 | 0.5104 |
 > ✅ **Key Advantage**:
 > By replacing large open-source models (e.g., Qwen3-32B) with **MemOperator-4B**, you can achieve **comparable or better memory processing performance** while reducing **resource consumption by over 80%** (4B vs 32B). This enables efficient, scalable, and cost-effective deployment.
@@ -93,6 +92,7 @@ config = SimpleStructMemReaderConfig(
                 "max_tokens": 6000,
                 "top_p": 0.95,
                 "top_k": 20,
             },
         },
         "embedder": {

 | **MemOperator-1.7B** | **0.7571** | **0.8068** | **0.6560** | **0.7955** | **0.5521** |
 | **MemOperator-0.6B** | **0.6753** | **0.6635** | **0.5780** | **0.7325** | **0.5000** |
 | GPT-4o-mini | 0.7405 | 0.7217 | 0.6844 | 0.7864 | 0.5659 |
 > ✅ **Key Advantage**:
 > By replacing large open-source models (e.g., Qwen3-32B) with **MemOperator-4B**, you can achieve **comparable or better memory processing performance** while reducing **resource consumption by over 80%** (4B vs 32B). This enables efficient, scalable, and cost-effective deployment.
                 "max_tokens": 6000,
                 "top_p": 0.95,
                 "top_k": 20,
+                "extra_body": {"chat_template_kwargs": {"enable_thinking": false}}
             },
         },
         "embedder": {