Instructions to use amewebstudio/ananke-sclm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amewebstudio/ananke-sclm with Transformers:

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

pipe = pipeline("text-generation", model="amewebstudio/ananke-sclm")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("amewebstudio/ananke-sclm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amewebstudio/ananke-sclm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/amewebstudio/ananke-sclm

SGLang

How to use amewebstudio/ananke-sclm 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 "amewebstudio/ananke-sclm" \
    --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": "amewebstudio/ananke-sclm",
		"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 "amewebstudio/ananke-sclm" \
        --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": "amewebstudio/ananke-sclm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amewebstudio/ananke-sclm with Docker Model Runner:
```
docker model run hf.co/amewebstudio/ananke-sclm
```

amewebstudio commited on Dec 17, 2025

Commit

a5f84ad

verified ·

1 Parent(s): fb59a28

SCLM v2 - Stateful Coherent Language Model with EARCP

Browse files

Files changed (1) hide show

earcp_weights.pt +1 -1

earcp_weights.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d9091ab46c47a4585f12b0b61f00f176e7610ab1c3554314c7a0d91ecbd41e
 size 366837710

 version https://git-lfs.github.com/spec/v1
+oid sha256:31515083ae0b204d0dfe24e27b95d9e410dabd92c00ec4cfb21e9587dce8e63d
 size 366837710