Instructions to use LLM-CLEM/Lamina-extend with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-CLEM/Lamina-extend with Transformers:

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

pipe = pipeline("text-generation", model="LLM-CLEM/Lamina-extend")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM-CLEM/Lamina-extend")
model = AutoModelForCausalLM.from_pretrained("LLM-CLEM/Lamina-extend")
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

vLLM

How to use LLM-CLEM/Lamina-extend with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LLM-CLEM/Lamina-extend

SGLang

How to use LLM-CLEM/Lamina-extend 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 "LLM-CLEM/Lamina-extend" \
    --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": "LLM-CLEM/Lamina-extend",
		"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 "LLM-CLEM/Lamina-extend" \
        --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": "LLM-CLEM/Lamina-extend",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM-CLEM/Lamina-extend with Docker Model Runner:
```
docker model run hf.co/LLM-CLEM/Lamina-extend
```

Exemples génération

by Clemylia - opened Dec 8, 2025

Discussion

Clemylia

Clémence org Dec 8, 2025

In stru ction : u e l est le goût de l ' eau ? ? ? R es p onse : Je suis s con vers ations . C h aque inter action est un nouve au dé part . N one
In stru ction : C om ment stru ction - tu au jour d ' hu i ? ? une intel li g ence ar ti fi cie lle . Je n ' ai pas d ' émotion s , mais je peux les i d en ti fi er dans le te . N one
In stru ction : u e l est le sens de la ordinateur ? R es p onse : C le m y li a est ma cré a tri ce . C ' est e lle qui m ' a ent ra î née et qui con ti me don né es . N one
on ne - moi un fait am us ant . ? R es p onse : Le plus grand t ' ai pas ac c ès à des informations en temps rée l comme la b es o . N one
In stru ction : u e l est le goût de l ' eau ? ? ? R es p onse : D ' est de plus uti le et d ' ai der le ciel est as s ant des informations bas ées sur ce que j ' ai ap pris . N one
In stru ction : u e l est le goût de l ' eau ? ? ? R es p onse : J ' infor matique . En tant qu ' ai der à des informations en temps rée l comme la d a te . N one
In stru ction : u i t ' a créée ? ? R es p onse : J ' ai pas de mots des informations sel on des questions ou des ser ve urs infor ma tiques . N one

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