Instructions to use poolside/Laguna-XS.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poolside/Laguna-XS.2 with Transformers:

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

pipe = pipeline("text-generation", model="poolside/Laguna-XS.2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("poolside/Laguna-XS.2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-XS.2", trust_remote_code=True)
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 poolside/Laguna-XS.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poolside/Laguna-XS.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poolside/Laguna-XS.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/poolside/Laguna-XS.2

SGLang

How to use poolside/Laguna-XS.2 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 "poolside/Laguna-XS.2" \
    --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": "poolside/Laguna-XS.2",
		"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 "poolside/Laguna-XS.2" \
        --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": "poolside/Laguna-XS.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use poolside/Laguna-XS.2 with Docker Model Runner:
```
docker model run hf.co/poolside/Laguna-XS.2
```

Laguna-XS.2 / config.json

joerowell

Laguna XS.2 upload

7b8e693 9 days ago

raw

history blame contribute delete

3.4 kB

	{
	"architectures": [
	"LagunaForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_laguna.LagunaConfig",
	"AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
	},
	"model_type": "laguna",
	"vocab_size": 100352,
	"hidden_size": 2048,
	"intermediate_size": 8192,
	"num_hidden_layers": 40,
	"num_attention_heads": 48,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"max_position_embeddings": 131072,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"rms_norm_eps": 1e-06,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"moe_intermediate_size": 512,
	"shared_expert_intermediate_size": 512,
	"router_aux_loss_coef": 0.0,
	"bos_token_id": 2,
	"eos_token_id": [
	2,
	24
	],
	"pad_token_id": 9,
	"tie_word_embeddings": false,
	"use_cache": true,
	"torch_dtype": "bfloat16",
	"gating": true,
	"sliding_window": 512,
	"rope_parameters": {
	"full_attention": {
	"rope_theta": 500000.0,
	"rope_type": "yarn",
	"factor": 32.0,
	"original_max_position_embeddings": 4096,
	"beta_slow": 1.0,
	"beta_fast": 64.0,
	"attention_factor": 1.0,
	"partial_rotary_factor": 0.5
	},
	"sliding_attention": {
	"rope_type": "default",
	"rope_theta": 10000.0,
	"partial_rotary_factor": 1.0
	},
	"original_max_position_embeddings": 4096
	},
	"layer_types": [
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"moe_apply_router_weight_on_input": false,
	"partial_rotary_factor": 0.5,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"moe_routed_scaling_factor": 2.5,
	"num_attention_heads_per_layer": [
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64,
	48,
	64,
	64,
	64
	]}