Instructions to use openeurollm/kda-sigmoid-hybrid-1.3B-100B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openeurollm/kda-sigmoid-hybrid-1.3B-100B with Transformers:

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

pipe = pipeline("text-generation", model="openeurollm/kda-sigmoid-hybrid-1.3B-100B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openeurollm/kda-sigmoid-hybrid-1.3B-100B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openeurollm/kda-sigmoid-hybrid-1.3B-100B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openeurollm/kda-sigmoid-hybrid-1.3B-100B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openeurollm/kda-sigmoid-hybrid-1.3B-100B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openeurollm/kda-sigmoid-hybrid-1.3B-100B

SGLang

How to use openeurollm/kda-sigmoid-hybrid-1.3B-100B 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 "openeurollm/kda-sigmoid-hybrid-1.3B-100B" \
    --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": "openeurollm/kda-sigmoid-hybrid-1.3B-100B",
		"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 "openeurollm/kda-sigmoid-hybrid-1.3B-100B" \
        --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": "openeurollm/kda-sigmoid-hybrid-1.3B-100B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openeurollm/kda-sigmoid-hybrid-1.3B-100B with Docker Model Runner:
```
docker model run hf.co/openeurollm/kda-sigmoid-hybrid-1.3B-100B
```

korbip commited on 9 days ago

Commit

aed831d

verified ·

1 Parent(s): 1b9ccd8

Add paper banner, figure and precise model descriptions

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +14 -1
complexkda.png +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+complexkda.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -6,11 +6,24 @@ tags:
 - complex-kda
 - linear-attention
 - kimi-delta-attention
 ---
 # openeurollm/kda-sigmoid-hybrid-1.3B-100B
-A hybrid ComplexKDA language model (1.36B parameters).
 ComplexKDA is Kimi Delta Attention with a **signed decay gate**: the per-channel
 decay `alpha` is allowed to take either sign, `alpha in [-1, 1]`, instead of

 - complex-kda
 - linear-attention
 - kimi-delta-attention
+- arxiv:2609.24797
 ---
 # openeurollm/kda-sigmoid-hybrid-1.3B-100B
+[![Paper](https://img.shields.io/static/v1?label=Paper&message=2609.24797&color=B31B1B&logo=arXiv)](https://arxiv.org/abs/2609.24797)
+[![GitHub](https://img.shields.io/github/stars/OpenEuroLLM/ComplexKDA)](https://github.com/OpenEuroLLM/ComplexKDA)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+> **Paper:** https://arxiv.org/abs/2609.24797
+>
+> **Code:** https://github.com/OpenEuroLLM/ComplexKDA
+>
+> **Authors:** Julien Siems, Riccardo Grazzi, Korbinian Pöppel, Jaisidh Singh, Arber Zela, Timur Carstensen, Jenia Jitsev, Frank Hutter, Volkan Cevher, Antonio Orvieto, Aaron Klein
+A **KDA baseline** (bounded sigmoid gate) hybrid language model (1.36B parameters) -- linear layers with full attention every 4th layer -- from the ComplexKDA release.
+<img src="complexkda.png" width="900" alt="ComplexKDA">
 ComplexKDA is Kimi Delta Attention with a **signed decay gate**: the per-channel
 decay `alpha` is allowed to take either sign, `alpha in [-1, 1]`, instead of

complexkda.png ADDED Viewed

Git LFS Details

SHA256: 944483d6510e45be3fae8176b6ba5d54a8195f116d61dc28da3c9edd6b0c72e6
Pointer size: 131 Bytes
Size of remote file: 455 kB