Instructions to use ethicalabs/Echo-DSRN-114M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ethicalabs/Echo-DSRN-114M-Base with Transformers:

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

pipe = pipeline("text-generation", model="ethicalabs/Echo-DSRN-114M-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ethicalabs/Echo-DSRN-114M-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ethicalabs/Echo-DSRN-114M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ethicalabs/Echo-DSRN-114M-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ethicalabs/Echo-DSRN-114M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ethicalabs/Echo-DSRN-114M-Base

SGLang

How to use ethicalabs/Echo-DSRN-114M-Base 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 "ethicalabs/Echo-DSRN-114M-Base" \
    --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": "ethicalabs/Echo-DSRN-114M-Base",
		"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 "ethicalabs/Echo-DSRN-114M-Base" \
        --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": "ethicalabs/Echo-DSRN-114M-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ethicalabs/Echo-DSRN-114M-Base with Docker Model Runner:
```
docker model run hf.co/ethicalabs/Echo-DSRN-114M-Base
```

Echo-DSRN-114M-Base v0.1.1

by mrs83 - opened Apr 15

Discussion

mrs83

ethicalabs.ai org Apr 15

We are currently pushing a major architectural fix for the Echo-DSRN-114M-Base model .

What was happening? The core of the DSRN architecture relies on a continuous memory bottleneck controlled by the surprise_lambda gate.

Under heavy TBPTT scaling, this raw parameter slipped into negative values, tricking the recurrent engine into mathematically "inverting" its prior state.

We have refactored the paramete and clamped it entirely through a F.softplus activation boundary. This guarantees that the memory gate remains strictly positive.

We've re-aligned the entire codebase and are currently recompiling the 114M-Base on 6B FineWeb Web + SmolTalk2 tokens

mrs83

ethicalabs.ai org Apr 15

v0.1.2 base model is ready

mrs83 changed discussion status to closed Apr 15

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment