Instructions to use MonumentalSystems/Ouroboros-1MContext-Gemma-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MonumentalSystems/Ouroboros-1MContext-Gemma-270m with Transformers:

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

pipe = pipeline("text-generation", model="MonumentalSystems/Ouroboros-1MContext-Gemma-270m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MonumentalSystems/Ouroboros-1MContext-Gemma-270m")
model = AutoModelForCausalLM.from_pretrained("MonumentalSystems/Ouroboros-1MContext-Gemma-270m", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MonumentalSystems/Ouroboros-1MContext-Gemma-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MonumentalSystems/Ouroboros-1MContext-Gemma-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MonumentalSystems/Ouroboros-1MContext-Gemma-270m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MonumentalSystems/Ouroboros-1MContext-Gemma-270m

SGLang

How to use MonumentalSystems/Ouroboros-1MContext-Gemma-270m 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 "MonumentalSystems/Ouroboros-1MContext-Gemma-270m" \
    --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": "MonumentalSystems/Ouroboros-1MContext-Gemma-270m",
		"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 "MonumentalSystems/Ouroboros-1MContext-Gemma-270m" \
        --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": "MonumentalSystems/Ouroboros-1MContext-Gemma-270m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MonumentalSystems/Ouroboros-1MContext-Gemma-270m with Docker Model Runner:
```
docker model run hf.co/MonumentalSystems/Ouroboros-1MContext-Gemma-270m
```

LisaMegaWatts commited on Mar 19

Commit

09a6480

verified ·

1 Parent(s): 34d9e65

Add model card with architecture details and LoRA config

Browse files

Files changed (1) hide show

README.md +60 -0

README.md ADDED Viewed

	@@ -0,0 +1,60 @@

+---
+language: en
+license: apache-2.0
+tags:
+- gemma3
+- causal-lm
+- 1m-context
+- symbiogenesis
+- episodic-memory
+base_model: google/gemma-3-270m
+library_name: transformers
+---
+# Ouroboros-1MContext-Gemma-270m
+1M-context extension of Google's [Gemma 3 270M](https://huggingface.co/google/gemma-3-270m) for episodic memory research.
+## Architecture
+| Parameter | Value |
+|---|---|
+| Model type | Gemma3ForCausalLM |
+| Hidden size | 640 |
+| Intermediate size | 2048 |
+| Num layers | 18 |
+| Num attention heads | 4 (GQA, 1 KV head) |
+| Head dim | 256 |
+| Vocab size | 262,144 |
+| Max position embeddings | 1,048,576 (1M context) |
+| Total parameters | 268,098,176 |
+| VRAM (bfloat16) | 0.54 GB |
+## LoRA Adapter Configuration (for episodic memory)
+| Parameter | Value |
+|---|---|
+| Rank | 4 |
+| Alpha | 8 |
+| Target modules | gate_proj, up_proj, down_proj |
+| Params per adapter | 580,608 |
+| Per LoRA pair (one layer, one module) | 10,752 |
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("MonumentalSystems/Ouroboros-1MContext-Gemma-270m", torch_dtype="bfloat16")
+tokenizer = AutoTokenizer.from_pretrained("MonumentalSystems/Ouroboros-1MContext-Gemma-270m")
+```
+## Citation
+Used in "Continuous Memory: Zero-Forgetting Episodic Memory via Per-Memory LoRA Adapters" (ICLR 2026 submission).
+W&B runs: `41uzevnn`, `oa8xe89e`, `2v01e4e9` (project: symbiogenesis)
+## License
+Apache 2.0 (following Gemma 3 license)