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

1b9ccd8

verified ·

1 Parent(s): 51088a3

Point the fla fork at OpenEuroLLM/ComplexKDA

Browse files

Files changed (2) hide show

README.md +1 -1
modeling_complex_kda.py +3 -3

README.md CHANGED Viewed

@@ -62,7 +62,7 @@ For the Triton kernels these models were trained with -- much faster, and the
 exact code path of the training runs -- install the fork:
 ```bash
-pip install git+https://github.com/automl/ComplexKDA
 ```
 It is picked up automatically when importable. `COMPLEX_KDA_BACKEND=torch`

 exact code path of the training runs -- install the fork:
 ```bash
+pip install git+https://github.com/OpenEuroLLM/ComplexKDA
 ```
 It is picked up automatically when importable. `COMPLEX_KDA_BACKEND=torch`

modeling_complex_kda.py CHANGED Viewed

@@ -13,7 +13,7 @@ else installed.
 IT GOES FASTER WITH THE FORK. When `fla` from
-    https://github.com/automl/ComplexKDA
 is importable, the Triton kernels and fused modules it ships are used instead,
 and the model is then running exactly the code the checkpoints were trained
@@ -117,7 +117,7 @@ if _REQUESTED == "kernel" and not HAS_KERNEL:
     raise ImportError(
         "COMPLEX_KDA_BACKEND=kernel, but the ComplexKDA fla fork's signed kernels are not "
         "available (need a CUDA device, triton, and `pip install "
-        "git+https://github.com/automl/ComplexKDA`).")
 USE_KERNEL = HAS_KERNEL and _REQUESTED != "torch"
 # Chunk length of the portable recurrence. It trades memory for sequential
@@ -133,7 +133,7 @@ if not USE_KERNEL:
     logger.warning_once(
         "ComplexKDA is running its portable torch implementation. For the Triton kernels the "
         "models were trained with, install the fork: "
-        "`pip install git+https://github.com/automl/ComplexKDA` (and set "
         "COMPLEX_KDA_BACKEND=torch to keep this path).")

 IT GOES FASTER WITH THE FORK. When `fla` from
+    https://github.com/OpenEuroLLM/ComplexKDA
 is importable, the Triton kernels and fused modules it ships are used instead,
 and the model is then running exactly the code the checkpoints were trained
     raise ImportError(
         "COMPLEX_KDA_BACKEND=kernel, but the ComplexKDA fla fork's signed kernels are not "
         "available (need a CUDA device, triton, and `pip install "
+        "git+https://github.com/OpenEuroLLM/ComplexKDA`).")
 USE_KERNEL = HAS_KERNEL and _REQUESTED != "torch"
 # Chunk length of the portable recurrence. It trades memory for sequential
     logger.warning_once(
         "ComplexKDA is running its portable torch implementation. For the Triton kernels the "
         "models were trained with, install the fork: "
+        "`pip install git+https://github.com/OpenEuroLLM/ComplexKDA` (and set "
         "COMPLEX_KDA_BACKEND=torch to keep this path).")